arXiv subjects

Xu Tan

Publications and source records attributed to Xu Tan.

At least 109 records · Page 6Linked to original sources

arXiv2023

FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output based on continuous speech features, complex VAE or flow-based models are usually required. In this paper, we propose FoundationTTS, a new speech synthesis system with a neural audio codec for discrete speech token extraction and waveform reconstruction and a large language model for discrete token generation from linguistic (phoneme) tokens. Specifically, 1) we propose a hierarchical codec network based on vector-quantized auto-encoders with adversarial training (VQ-GAN), which first extracts continuous frame-level speech representations with fine-grained codec, and extracts a discrete token from each continuous speech frame with coarse-grained codec; 2) we jointly optimize speech token, linguistic tokens, speaker token together with a large language model and predict the discrete speech tokens autoregressively. Experiments show that FoundationTTS achieves a MOS gain of +0.14 compared to the baseline system. In ASR customization tasks, our method achieves 7.09\% and 10.35\% WERR respectively over two strong customized ASR baselines.

eess.AS↗

arXiv2023

A Study on ReLU and Softmax in Transformer

The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and traditional memory utilize different activation functions (i.e., ReLU and Softmax respectively), which makes them not equivalent. In this paper, we first rebuild the connections between FFN and key-value memory by conducting extensive studies on ReLU and Softmax, and find they are equivalent when adding an additional layer normalization module on Softmax. In addition, ReLU outperforms Softmax on both FFN and key-value memory when the number of value slots is large. We analyze the reasons and then explore this good property of ReLU on the self-attention network where the original Softmax activation performs poorly on long input sequences. We then propose a full ReLU architecture named ReLUFormer which performs better than the baseline Transformer on long sequence tasks such as document translation. This paper sheds light on the following points: 1) Softmax and ReLU use different normalization methods over elements which lead to different variances of results, and ReLU is good at dealing with a large number of key-value slots; 2) FFN and key-value memory are equivalent, and thus the Transformer can be viewed as a memory network where FFNs and self-attention networks are both key-value memories.

cs.CL↗

arXiv2023

N-Gram Nearest Neighbor Machine Translation

Nearest neighbor machine translation augments the Autoregressive Translation~(AT) with $k$-nearest-neighbor retrieval, by comparing the similarity between the token-level context representations of the target tokens in the query and the datastore. However, the token-level representation may introduce noise when translating ambiguous words, or fail to provide accurate retrieval results when the representation generated by the model contains indistinguishable context information, e.g., Non-Autoregressive Translation~(NAT) models. In this paper, we propose a novel $n$-gram nearest neighbor retrieval method that is model agnostic and applicable to both AT and NAT models. Specifically, we concatenate the adjacent $n$-gram hidden representations as the key, while the tuple of corresponding target tokens is the value. In inference, we propose tailored decoding algorithms for AT and NAT models respectively. We demonstrate that the proposed method consistently outperforms the token-level method on both AT and NAT models as well on general as on domain adaptation translation tasks. On domain adaptation, the proposed method brings $1.03$ and $2.76$ improvements regarding the average BLEU score on AT and NAT models respectively.

cs.CL↗

arXiv2023

Re-creation of Creations: A New Paradigm for Lyric-to-Melody Generation

Lyric-to-melody generation is an important task in songwriting, and is also quite challenging due to its unique characteristics: the generated melodies should not only follow good musical patterns, but also align with features in lyrics such as rhythms and structures. These characteristics cannot be well handled by neural generation models that learn lyric-to-melody mapping in an end-to-end way, due to several issues: (1) lack of aligned lyric-melody training data to sufficiently learn lyric-melody feature alignment; (2) lack of controllability in generation to better and explicitly align the lyric-melody features. In this paper, we propose Re-creation of Creations (ROC), a new paradigm for lyric-to-melody generation. ROC generates melodies according to given lyrics and also conditions on user-designated chord progression. It addresses the above issues through a generation-retrieval pipeline. Specifically, our paradigm has two stages: (1) creation stage, where a huge amount of music fragments generated by a neural melody language model are indexed in a database through several key features (e.g., chords, tonality, rhythm, and structural information); (2) re-creation stage, where melodies are re-created by retrieving music fragments from the database according to the key features from lyrics and concatenating best music fragments based on composition guidelines and melody language model scores. ROC has several advantages: (1) It only needs unpaired melody data to train melody language model, instead of paired lyric-melody data in previous models. (2) It achieves good lyric-melody feature alignment in lyric-to-melody generation. Tested by English and Chinese lyrics, ROC outperforms previous neural based lyric-to-melody generation models on both objective and subjective metrics.

cs.SD↗

arXiv2023

Regeneration Learning: A Learning Paradigm for Data Generation

Machine learning methods for conditional data generation usually build a mapping from source conditional data X to target data Y. The target Y (e.g., text, speech, music, image, video) is usually high-dimensional and complex, and contains information that does not exist in source data, which hinders effective and efficient learning on the source-target mapping. In this paper, we present a learning paradigm called regeneration learning for data generation, which first generates Y' (an abstraction/representation of Y) from X and then generates Y from Y'. During training, Y' is obtained from Y through either handcrafted rules or self-supervised learning and is used to learn X-->Y' and Y'-->Y. Regeneration learning extends the concept of representation learning to data generation tasks, and can be regarded as a counterpart of traditional representation learning, since 1) regeneration learning handles the abstraction (Y') of the target data Y for data generation while traditional representation learning handles the abstraction (X') of source data X for data understanding; 2) both the processes of Y'-->Y in regeneration learning and X-->X' in representation learning can be learned in a self-supervised way (e.g., pre-training); 3) both the mappings from X to Y' in regeneration learning and from X' to Y in representation learning are simpler than the direct mapping from X to Y. We show that regeneration learning can be a widely-used paradigm for data generation (e.g., text generation, speech recognition, speech synthesis, music composition, image generation, and video generation) and can provide valuable insights into developing data generation methods.

cs.LG↗

arXiv2022

ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusion model which learns to refine the output spectrogram of an existing TTS model (e.g., FastSpeech 2) by predicting the residual between the model output and the corresponding ground-truth speech. ResGrad has several advantages: 1) Compare with other acceleration methods for DDPM which need to synthesize speech from scratch, ResGrad reduces the complexity of task by changing the generation target from ground-truth mel-spectrogram to the residual, resulting into a more lightweight model and thus a smaller real-time factor. 2) ResGrad is employed in the inference process of the existing TTS model in a plug-and-play way, without re-training this model. We verify ResGrad on the single-speaker dataset LJSpeech and two more challenging datasets with multiple speakers (LibriTTS) and high sampling rate (VCTK). Experimental results show that in comparison with other speed-up methods of DDPMs: 1) ResGrad achieves better sample quality with the same inference speed measured by real-time factor; 2) with similar speech quality, ResGrad synthesizes speech faster than baseline methods by more than 10 times. Audio samples are available at https://resgrad1.github.io/.

eess.AS↗

arXiv2022

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR outputs. Previous works usually use a sequence-to-sequence model to correct an ASR output sentence autoregressively, which causes large latency and cannot be deployed in online ASR services. A straightforward solution to reduce latency, inspired by non-autoregressive (NAR) neural machine translation, is to use an NAR sequence generation model for ASR error correction, which, however, comes at the cost of significantly increased ASR error rate. In this paper, observing distinctive error patterns and correction operations (i.e., insertion, deletion, and substitution) in ASR, we propose FastCorrect, a novel NAR error correction model based on edit alignment. In training, FastCorrect aligns each source token from an ASR output sentence to the target tokens from the corresponding ground-truth sentence based on the edit distance between the source and target sentences, and extracts the number of target tokens corresponding to each source token during edition/correction, which is then used to train a length predictor and to adjust the source tokens to match the length of the target sentence for parallel generation. In inference, the token number predicted by the length predictor is used to adjust the source tokens for target sequence generation. Experiments on the public AISHELL-1 dataset and an internal industrial-scale ASR dataset show the effectiveness of FastCorrect for ASR error correction: 1) it speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model; and 2) it outperforms the popular NAR models adopted in neural machine translation and text edition by a large margin.

cs.CL↗

arXiv2022

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens. In this work, we propose FastCorrect 2, an error correction model that takes multiple ASR candidates as input for better correction accuracy. FastCorrect 2 adopts non-autoregressive generation for fast inference, which consists of an encoder that processes multiple source sentences and a decoder that generates the target sentence in parallel from the adjusted source sentence, where the adjustment is based on the predicted duration of each source token. However, there are some issues when handling multiple source sentences. First, it is non-trivial to leverage the voting effect from multiple source sentences since they usually vary in length. Thus, we propose a novel alignment algorithm to maximize the degree of token alignment among multiple sentences in terms of token and pronunciation similarity. Second, the decoder can only take one adjusted source sentence as input, while there are multiple source sentences. Thus, we develop a candidate predictor to detect the most suitable candidate for the decoder. Experiments on our inhouse dataset and AISHELL-1 show that FastCorrect 2 can further reduce the WER over the previous correction model with single candidate by 3.2% and 2.6%, demonstrating the effectiveness of leveraging multiple candidates in ASR error correction. FastCorrect 2 achieves better performance than the cascaded re-scoring and correction pipeline and can serve as a unified post-processing module for ASR.

cs.CL↗

arXiv2022

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtrations, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models),the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: 0.128 vs. 0.157, MOS: 3.80 vs. 3.61). The generated audio samples (https://speechresearch.github.io/binauralgrad) and code (https://github.com/microsoft/NeuralSpeech/tree/master/BinauralGrad) are available online.

eess.AS↗

arXiv2022

Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction

Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models. Previous error correction methods usually take the source (incorrect) sentence as encoder input and generate the target (correct) sentence through the decoder. Since the error rate of the incorrect sentence is usually low (e.g., 10\%), the correction model can only learn to correct on limited error tokens but trivially copy on most tokens (correct tokens), which harms the effective training of error correction. In this paper, we argue that the correct tokens should be better utilized to facilitate effective training and then propose a simple yet effective masking strategy to achieve this goal. Specifically, we randomly mask out a part of the correct tokens in the source sentence and let the model learn to not only correct the original error tokens but also predict the masked tokens based on their context information. Our method enjoys several advantages: 1) it alleviates trivial copy; 2) it leverages effective training signals from correct tokens; 3) it is a plug-and-play module and can be applied to different models and tasks. Experiments on spelling error correction and speech recognition error correction on Mandarin datasets and grammar error correction on English datasets with both autoregressive and non-autoregressive generation models show that our method improves the correction accuracy consistently.

cs.CL↗

arXiv2022

PromptTTS: Controllable Text-to-Speech with Text Descriptions

Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utilizing text descriptions to guide speech synthesis. Thus, we develop a text-to-speech (TTS) system (dubbed as PromptTTS) that takes a prompt with both style and content descriptions as input to synthesize the corresponding speech. Specifically, PromptTTS consists of a style encoder and a content encoder to extract the corresponding representations from the prompt, and a speech decoder to synthesize speech according to the extracted style and content representations. Compared with previous works in controllable TTS that require users to have acoustic knowledge to understand style factors such as prosody and pitch, PromptTTS is more user-friendly since text descriptions are a more natural way to express speech style (e.g., ''A lady whispers to her friend slowly''). Given that there is no TTS dataset with prompts, to benchmark the task of PromptTTS, we construct and release a dataset containing prompts with style and content information and the corresponding speech. Experiments show that PromptTTS can generate speech with precise style control and high speech quality. Audio samples and our dataset are publicly available.

eess.AS↗

arXiv2022

TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method

Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a template-to-melody module). TeleMelody has two advantages. First, it is data efficient. The template-to-melody module is trained in a self-supervised way (i.e., the source template is extracted from the target melody) that does not need any lyric-melody paired data. The lyric-to-template module is made up of some rules and a lyric-to-rhythm model, which is trained with paired lyric-rhythm data that is easier to obtain than paired lyric-melody data. Second, it is controllable. The design of template ensures that the generated melodies can be controlled by adjusting the musical elements in template. Both subjective and objective experimental evaluations demonstrate that TeleMelody generates melodies with higher quality, better controllability, and less requirement on paired lyric-melody data than previous generation systems.

cs.SD↗

arXiv2022

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

Symbolic music generation aims to generate music scores automatically. A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the typically long music sequences (e.g., over 10,000 tokens), and the existing models have shortcomings in generating musical repetition structures. In this paper, we propose Museformer, a Transformer with a novel fine- and coarse-grained attention for music generation. Specifically, with the fine-grained attention, a token of a specific bar directly attends to all the tokens of the bars that are most relevant to music structures (e.g., the previous 1st, 2nd, 4th and 8th bars, selected via similarity statistics); with the coarse-grained attention, a token only attends to the summarization of the other bars rather than each token of them so as to reduce the computational cost. The advantages are two-fold. First, it can capture both music structure-related correlations via the fine-grained attention, and other contextual information via the coarse-grained attention. Second, it is efficient and can model over 3X longer music sequences compared to its full-attention counterpart. Both objective and subjective experimental results demonstrate its ability to generate long music sequences with high quality and better structures.

cs.SD↗

arXiv2022

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in many natural language processing scenarios, like reranking, which is to select the best sentence from multiple candidates. Previous works on sentence scoring mainly adopted either causal language modeling (CLM) like GPT or masked language modeling (MLM) like BERT, which have some limitations: 1) CLM only utilizes unidirectional information for the probability estimation of a sentence without considering bidirectional context, which affects the scoring quality; 2) MLM can only estimate the probability of partial tokens at a time and thus requires multiple forward passes to estimate the probability of the whole sentence, which incurs large computation and time cost. In this paper, we propose \textit{Transcormer} -- a Transformer model with a novel \textit{sliding language modeling} (SLM) for sentence scoring. Specifically, our SLM adopts a triple-stream self-attention mechanism to estimate the probability of all tokens in a sentence with bidirectional context and only requires a single forward pass. SLM can avoid the limitations of CLM (only unidirectional context) and MLM (multiple forward passes) and inherit their advantages, and thus achieve high effectiveness and efficiency in scoring. Experimental results on multiple tasks demonstrate that our method achieves better performance than other language modelings.

cs.CL↗

arXiv2022

MeloForm: Generating Melody with Musical Form based on Expert Systems and Neural Networks

Human usually composes music by organizing elements according to the musical form to express music ideas. However, for neural network-based music generation, it is difficult to do so due to the lack of labelled data on musical form. In this paper, we develop MeloForm, a system that generates melody with musical form using expert systems and neural networks. Specifically, 1) we design an expert system to generate a melody by developing musical elements from motifs to phrases then to sections with repetitions and variations according to pre-given musical form; 2) considering the generated melody is lack of musical richness, we design a Transformer based refinement model to improve the melody without changing its musical form. MeloForm enjoys the advantages of precise musical form control by expert systems and musical richness learning via neural models. Both subjective and objective experimental evaluations demonstrate that MeloForm generates melodies with precise musical form control with 97.79% accuracy, and outperforms baseline systems in terms of subjective evaluation score by 0.75, 0.50, 0.86 and 0.89 in structure, thematic, richness and overall quality, without any labelled musical form data. Besides, MeloForm can support various kinds of forms, such as verse and chorus form, rondo form, variational form, sonata form, etc.

cs.SD↗

arXiv2022

StableFace: Analyzing and Improving Motion Stability for Talking Face Generation

While previous speech-driven talking face generation methods have made significant progress in improving the visual quality and lip-sync quality of the synthesized videos, they pay less attention to lip motion jitters which greatly undermine the realness of talking face videos. What causes motion jitters, and how to mitigate the problem? In this paper, we conduct systematic analyses on the motion jittering problem based on a state-of-the-art pipeline that uses 3D face representations to bridge the input audio and output video, and improve the motion stability with a series of effective designs. We find that several issues can lead to jitters in synthesized talking face video: 1) jitters from the input 3D face representations; 2) training-inference mismatch; 3) lack of dependency modeling among video frames. Accordingly, we propose three effective solutions to address this issue: 1) we propose a gaussian-based adaptive smoothing module to smooth the 3D face representations to eliminate jitters in the input; 2) we add augmented erosions on the input data of the neural renderer in training to simulate the distortion in inference to reduce mismatch; 3) we develop an audio-fused transformer generator to model dependency among video frames. Besides, considering there is no off-the-shelf metric for measuring motion jitters in talking face video, we devise an objective metric (Motion Stability Index, MSI), to quantitatively measure the motion jitters by calculating the reciprocal of variance acceleration. Extensive experimental results show the superiority of our method on motion-stable face video generation, with better quality than previous systems.

cs.CV↗

arXiv2022

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.

eess.AS↗

arXiv2022

Analyzing and Mitigating Interference in Neural Architecture Search

Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However, the rank correlation between the estimated accuracy and ground truth accuracy of those child models is low due to the interference among different child models caused by weight sharing. In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe: 1) the interference on a shared operator between two child models is positively correlated with the number of different operators; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar. Inspired by these two observations, we propose two approaches to mitigate the interference: 1) MAGIC-T: rather than randomly sampling child models for optimization, we propose a gradual modification scheme by modifying one operator between adjacent optimization steps to minimize the interference on the shared operators; 2) MAGIC-A: forcing the inputs and outputs of the operator across all child models to be similar to reduce the interference. Experiments on a BERT search space verify that mitigating interference via each of our proposed methods improves the rank correlation of super-pet and combining both methods can achieve better results. Our discovered architecture outperforms RoBERTa$_{\rm base}$ by 1.1 and 0.6 points and ELECTRA$_{\rm base}$ by 1.6 and 1.1 points on the dev and test set of GLUE benchmark. Extensive results on the BERT compression, reading comprehension and ImageNet task demonstrate the effectiveness and generality of our proposed methods.

cs.CL↗