arXiv subjects

Kai Yu

Publications and source records attributed to Kai Yu.

At least 217 records · Page 12Linked to original sources

arXiv2024

Acoustic BPE for Speech Generation with Discrete Tokens

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of the token sequence. Additionally, this approach places the burden on the model to establish correlations between tokens, further complicating the modeling process. To address this issue, we propose acoustic BPE which encodes frequent audio token patterns by utilizing byte-pair encoding. Acoustic BPE effectively reduces the sequence length and leverages the prior morphological information present in token sequence, which alleviates the modeling challenges of token correlation. Through comprehensive investigations on a speech language model trained with acoustic BPE, we confirm the notable advantages it offers, including faster inference and improved syntax capturing capabilities. In addition, we propose a novel rescore method to select the optimal synthetic speech among multiple candidates generated by rich-diversity TTS system. Experiments prove that rescore selection aligns closely with human preference, which highlights acoustic BPE's potential to other speech generation tasks.

cs.SD↗

arXiv2024

DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder

Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.

cs.CV↗

arXiv2024

Contrastive Learning With Audio Discrimination For Customizable Keyword Spotting In Continuous Speech

Customizable keyword spotting (KWS) in continuous speech has attracted increasing attention due to its real-world application potential. While contrastive learning (CL) has been widely used to extract keyword representations, previous CL approaches all operate on pre-segmented isolated words and employ only audio-text representations matching strategy. However, for KWS in continuous speech, co-articulation and streaming word segmentation can easily yield similar audio patterns for different texts, which may consequently trigger false alarms. To address this issue, we propose a novel CL with Audio Discrimination (CLAD) approach to learning keyword representation with both audio-text matching and audio-audio discrimination ability. Here, an InfoNCE loss considering both audio-audio and audio-text CL data pairs is employed for each sliding window during training. Evaluations on the open-source LibriPhrase dataset show that the use of sliding-window level InfoNCE loss yields comparable performance compared to previous CL approaches. Furthermore, experiments on the continuous speech dataset LibriSpeech demonstrate that, by incorporating audio discrimination, CLAD achieves significant performance gain over CL without audio discrimination. Meanwhile, compared to two-stage KWS approaches, the end-to-end KWS with CLAD achieves not only better performance, but also significant speed-up.

eess.AS↗

arXiv2024

Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images

Focusing on the complicated pathological features, such as blurred boundaries, severe scale differences between symptoms, background noise interference, etc., in the task of retinal edema lesions joint segmentation from OCT images and enabling the segmentation results more reliable. In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network, which can provide accurate segmentation results with reliability assessment. Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed. Meanwhile, to make the segmentation results more reliable, a novel uncertainty segmentation head based on the subjective logical evidential theory is introduced to generate the final segmentation results with a corresponding overall uncertainty evaluation score map. We conduct comprehensive experiments on the public database of AI-Challenge 2018 for retinal edema lesions segmentation, and the results show that our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches. The code will be released on: https://github.com/LooKing9218/ReliableRESeg.

eess.IV↗

arXiv2023

Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ natural language processing techniques. However, these studies, mainly single-task focused, faced challenges like overfitting and performance degradation in speech recognition tasks, often at the cost of sacrificing performance in multi-task scenarios. This study presents a comprehensive comparison and optimization of discrete tokens generated by various leading SSL models in speech recognition and synthesis tasks. We aim to explore the universality of speech discrete tokens across multiple speech tasks. Experimental results demonstrate that discrete tokens achieve comparable results against systems trained on FBank features in speech recognition tasks and outperform mel-spectrogram features in speech synthesis in subjective and objective metrics. These findings suggest that universal discrete tokens have enormous potential in various speech-related tasks. Our work is open-source and publicly available at https://github.com/k2-fsa/icefall.

eess.AS↗

arXiv2023

DreaMoving: A Human Video Generation Framework based on Diffusion Models

In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos. Specifically, given target identity and posture sequences, DreaMoving can generate a video of the target identity moving or dancing anywhere driven by the posture sequences. To this end, we propose a Video ControlNet for motion-controlling and a Content Guider for identity preserving. The proposed model is easy to use and can be adapted to most stylized diffusion models to generate diverse results. The project page is available at https://dreamoving.github.io/dreamoving

cs.CV↗

arXiv2023

Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning

We present Boosting3D, a multi-stage single image-to-3D generation method that can robustly generate reasonable 3D objects in different data domains. The point of this work is to solve the view consistency problem in single image-guided 3D generation by modeling a reasonable geometric structure. For this purpose, we propose to utilize better 3D prior to training the NeRF. More specifically, we train an object-level LoRA for the target object using original image and the rendering output of NeRF. And then we train the LoRA and NeRF using a progressive training strategy. The LoRA and NeRF will boost each other while training. After the progressive training, the LoRA learns the 3D information of the generated object and eventually turns to an object-level 3D prior. In the final stage, we extract the mesh from the trained NeRF and use the trained LoRA to optimize the structure and appearance of the mesh. The experiments demonstrate the effectiveness of the proposed method. Boosting3D learns object-specific 3D prior which is beyond the ability of pre-trained diffusion priors and achieves state-of-the-art performance in the single image-to-3d generation task.

cs.CV↗

arXiv2023

Beyond the Status Quo: A Contemporary Survey of Advances and Challenges in Audio Captioning

Automated audio captioning (AAC), a task that mimics human perception as well as innovatively links audio processing and natural language processing, has overseen much progress over the last few years. AAC requires recognizing contents such as the environment, sound events and the temporal relationships between sound events and describing these elements with a fluent sentence. Currently, an encoder-decoder-based deep learning framework is the standard approach to tackle this problem. Plenty of works have proposed novel network architectures and training schemes, including extra guidance, reinforcement learning, audio-text self-supervised learning and diverse or controllable captioning. Effective data augmentation techniques, especially based on large language models are explored. Benchmark datasets and AAC-oriented evaluation metrics also accelerate the improvement of this field. This paper situates itself as a comprehensive survey covering the comparison between AAC and its related tasks, the existing deep learning techniques, datasets, and the evaluation metrics in AAC, with insights provided to guide potential future research directions.

cs.SD↗

arXiv2023

Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations

Expressive text-to-speech (TTS) aims to synthesize speeches with human-like tones, moods, or even artistic attributes. Recent advancements in expressive TTS empower users with the ability to directly control synthesis style through natural language prompts. However, these methods often require excessive training with a significant amount of style-annotated data, which can be challenging to acquire. Moreover, they may have limited adaptability due to fixed style annotations. In this work, we present FreeStyleTTS (FS-TTS), a controllable expressive TTS model with minimal human annotations. Our approach utilizes a large language model (LLM) to transform expressive TTS into a style retrieval task. The LLM selects the best-matching style references from annotated utterances based on external style prompts, which can be raw input text or natural language style descriptions. The selected reference guides the TTS pipeline to synthesize speeches with the intended style. This innovative approach provides flexible, versatile, and precise style control with minimal human workload. Experiments on a Mandarin storytelling corpus demonstrate FS-TTS's proficiency in leveraging LLM's semantic inference ability to retrieve desired styles from either input text or user-defined descriptions. This results in synthetic speeches that are closely aligned with the specified styles.

eess.AS↗

arXiv2023

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term experience memory, REMEMBERER is capable of exploiting the experiences from the past episodes even for different task goals, which excels an LLM-based agent with fixed exemplars or equipped with a transient working memory. We further introduce Reinforcement Learning with Experience Memory (RLEM) to update the memory. Thus, the whole system can learn from the experiences of both success and failure, and evolve its capability without fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER constitutes a semi-parametric RL agent. Extensive experiments are conducted on two RL task sets to evaluate the proposed framework. The average results with different initialization and training sets exceed the prior SOTA by 4% and 2% for the success rate on two task sets and demonstrate the superiority and robustness of REMEMBERER.

cs.CL↗

arXiv2023

ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL

Text-to-SQL aims to generate an executable SQL program given the user utterance and the corresponding database schema. To ensure the well-formedness of output SQLs, one prominent approach adopts a grammar-based recurrent decoder to produce the equivalent SQL abstract syntax tree (AST). However, previous methods mainly utilize an RNN-series decoder, which 1) is time-consuming and inefficient and 2) introduces very few structure priors. In this work, we propose an AST structure-aware Transformer decoder (ASTormer) to replace traditional RNN cells. The structural knowledge, such as node types and positions in the tree, is seamlessly incorporated into the decoder via both absolute and relative position embeddings. Besides, the proposed framework is compatible with different traversing orders even considering adaptive node selection. Extensive experiments on five text-to-SQL benchmarks demonstrate the effectiveness and efficiency of our structured decoder compared to competitive baselines.

cs.CL↗

arXiv2023

ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought

Recently Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks. We study the problem of prompt designing in the text-to-SQL task and attempt to improve the LLMs' reasoning ability when generating SQL queries. Besides the trivial few-shot in-context learning setting, we design our chain-of-thought (CoT) prompt with a similar method to schema linking. We provide a method named ACT-SQL to automatically generate auto-CoT exemplars and thus the whole process doesn't need manual labeling. Our approach is cost-saving since we only use the LLMs' API call once when generating one SQL query. Furthermore, we extend our in-context learning method to the multi-turn text-to-SQL task. The experiment results show that the LLMs' performance can benefit from our ACT-SQL approach. Our approach achieves SOTA performance on the Spider dev set among existing in-context learning approaches.

cs.CL↗

arXiv2023

Rich Prosody Diversity Modelling with Phone-level Mixture Density Network

Generating natural speech with diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the generated speech is still very limited and far from what can be achieved by human. This is largely due to the use of uni-modal distribution, such as single Gaussian, in the prior works of phone-level prosody modelling. In this work, we propose a novel approach that models phone-level prosodies with GMM based mixture density network (GMM-MDN). Experiments on the LJSpeech dataset demonstrate that phone-level prosodies can precisely control the synthetic speech and GMM-MDN can generate more natural and smooth prosody pattern than a single Gaussian. Subjective evaluations further show that the proposed approach not only achieves better naturalness, but also significantly improves the prosody diversity in synthetic speech without the need of manual control.

cs.SD↗

arXiv2023

Reliable Federated Disentangling Network for Non-IID Domain Feature

Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. However, the domain feature shift caused by different acquisition devices/clients substantially degrades the performance of the FL model. Furthermore, most existing FL approaches aim to improve accuracy without considering reliability (e.g., confidence or uncertainty). The predictions are thus unreliable when deployed in safety-critical applications. Therefore, aiming at improving the performance of FL in non-Domain feature issues while enabling the model more reliable. In this paper, we propose a novel reliable federated disentangling network, termed RFedDis, which utilizes feature disentangling to enable the ability to capture the global domain-invariant cross-client representation and preserve local client-specific feature learning. Meanwhile, to effectively integrate the decoupled features, an uncertainty-aware decision fusion is also introduced to guide the network for dynamically integrating the decoupled features at the evidence level, while producing a reliable prediction with an estimated uncertainty. To the best of our knowledge, our proposed RFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features. Extensive experimental results show that our proposed RFedDis provides outstanding performance with a high degree of reliability as compared to other state-of-the-art FL approaches.

cs.CV↗

arXiv2023

Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT). Existing TPT methods typically rely on data augmentation and confidence selection. However, conventional data augmentation techniques, e.g., random resized crops, suffers from the lack of data diversity, while entropy-based confidence selection alone is not sufficient to guarantee prediction fidelity. To address these issues, we propose a novel TPT method, named DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Specifically, we incorporate augmented data by both conventional method and pre-trained stable diffusion to exploit their respective merits, improving the models ability to adapt to unknown new test data. Moreover, to ensure the prediction fidelity of generated data, we introduce a cosine similarity-based filtration technique to select the generated data with higher similarity to the single test sample. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13\% compared to the state-of-the-art TPT method. Our code and models will be publicly released.

cs.CV↗

arXiv2023

Towards Instance-adaptive Inference for Federated Learning

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. However, the performance of the global model is often hampered by non-i.i.d. distribution among the clients, requiring extensive efforts to mitigate inter-client data heterogeneity. Going beyond inter-client data heterogeneity, we note that intra-client heterogeneity can also be observed on complex real-world data and seriously deteriorate FL performance. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Instead of huge instance-adaptive models, we resort to a parameter-efficient fine-tuning method, i.e., scale and shift deep features (SSF), upon a pre-trained model. Specifically, we first train an SSF pool for each client, and aggregate these SSF pools on the server side, thus still maintaining a low communication cost. To enable instance-adaptive inference, for a given instance, we dynamically find the best-matched SSF subsets from the pool and aggregate them to generate an adaptive SSF specified for the instance, thereby reducing the intra-client as well as the inter-client heterogeneity. Extensive experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64\% improvement against the top-performing method with less than 15\% communication cost on Tiny-ImageNet. Our code and models will be publicly released.

cs.LG↗

arXiv2023

DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech

Although high-fidelity speech can be obtained for intralingual speech synthesis, cross-lingual text-to-speech (CTTS) is still far from satisfactory as it is difficult to accurately retain the speaker timbres(i.e. speaker similarity) and eliminate the accents from their first language(i.e. nativeness). In this paper, we demonstrated that vector-quantized(VQ) acoustic feature contains less speaker information than mel-spectrogram. Based on this finding, we propose a novel dual speaker embedding TTS (DSE-TTS) framework for CTTS with authentic speaking style. Here, one embedding is fed to the acoustic model to learn the linguistic speaking style, while the other one is integrated into the vocoder to mimic the target speaker's timbre. Experiments show that by combining both embeddings, DSE-TTS significantly outperforms the state-of-the-art SANE-TTS in cross-lingual synthesis, especially in terms of nativeness.

cs.SD↗

arXiv2023

Improving Audio Caption Fluency with Automatic Error Correction

Automated audio captioning (AAC) is an important cross-modality translation task, aiming at generating descriptions for audio clips. However, captions generated by previous AAC models have faced ``false-repetition'' errors due to the training objective. In such scenarios, we propose a new task of AAC error correction and hope to reduce such errors by post-processing AAC outputs. To tackle this problem, we use observation-based rules to corrupt captions without errors, for pseudo grammatically-erroneous sentence generation. One pair of corrupted and clean sentences can thus be used for training. We train a neural network-based model on the synthetic error dataset and apply the model to correct real errors in AAC outputs. Results on two benchmark datasets indicate that our approach significantly improves fluency while maintaining semantic information.

eess.AS↗