arXiv subjects

Eng Siong Chng

Publications and source records attributed to Eng Siong Chng.

At least 145 records · Page 8Linked to original sources

arXiv2022

L-SpEx: Localized Target Speaker Extraction

Speaker extraction aims to extract the target speaker's voice from a multi-talker speech mixture given an auxiliary reference utterance. Recent studies show that speaker extraction benefits from the location or direction of the target speaker. However, these studies assume that the target speaker's location is known in advance or detected by an extra visual cue, e.g., face image or video. In this paper, we propose an end-to-end localized target speaker extraction on pure speech cues, that is called L-SpEx. Specifically, we design a speaker localizer driven by the target speaker's embedding to extract the spatial features, including direction-of-arrival (DOA) of the target speaker and beamforming output. Then, the spatial cues and target speaker's embedding are both used to form a top-down auditory attention to the target speaker. Experiments on the multi-channel reverberant dataset called MC-Libri2Mix show that our L-SpEx approach significantly outperforms the baseline system.

eess.AS↗

arXiv2022

An Embarrassingly Simple Model for Dialogue Relation Extraction

Dialogue relation extraction (RE) is to predict the relation type of two entities mentioned in a dialogue. In this paper, we propose a simple yet effective model named SimpleRE for the RE task. SimpleRE captures the interrelations among multiple relations in a dialogue through a novel input format named BERT Relation Token Sequence (BRS). In BRS, multiple [CLS] tokens are used to capture possible relations between different pairs of entities mentioned in the dialogue. A Relation Refinement Gate (RRG) is then designed to extract relation-specific semantic representation in an adaptive manner. Experiments on the DialogRE dataset show that SimpleRE achieves the best performance, with much shorter training time. Further, SimpleRE outperforms all direct baselines on sentence-level RE without using external resources.

cs.CL↗

arXiv2022

ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting

Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achieve noise robustness with concise neural operations. In a real-world application, the user environment is typically noisy and may also contain reverberations. We proposed a novel feature interactive convolutional model with merely 100K parameters to tackle this under the noisy far-field condition. The interactive unit is proposed in place of the attention module that promotes the flow of information with more efficient computations. Moreover, curriculum-based multi-condition training is adopted to attain better noise robustness. Our model achieves 98.2% top-1 accuracy on Google Speech Command V2-12 and is competitive against large transformer models under the designed noise condition.

cs.SD↗

arXiv2021

A Unified Speaker Adaptation Approach for ASR

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a trained model with target speaker data is the most natural approach for adaptation, but it takes a lot of compute and may cause catastrophic forgetting to the existing speakers. In this work, we propose a unified speaker adaptation approach consisting of feature adaptation and model adaptation. For feature adaptation, we employ a speaker-aware persistent memory model which generalizes better to unseen test speakers by making use of speaker i-vectors to form a persistent memory. For model adaptation, we use a novel gradual pruning method to adapt to target speakers without changing the model architecture, which to the best of our knowledge, has never been explored in ASR. Specifically, we gradually prune less contributing parameters on model encoder to a certain sparsity level, and use the pruned parameters for adaptation, while freezing the unpruned parameters to keep the original model performance. We conduct experiments on the Librispeech dataset. Our proposed approach brings relative 2.74-6.52% word error rate (WER) reduction on general speaker adaptation. On target speaker adaptation, our method outperforms the baseline with up to 20.58% relative WER reduction, and surpasses the finetuning method by up to relative 2.54%. Besides, with extremely low-resource adaptation data (e.g., 1 utterance), our method could improve the WER by relative 6.53% with only a few epochs of training.

eess.AS↗

arXiv2021

Minimum word error training for non-autoregressive Transformer-based code-switching ASR

Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones. However, it still under-performs the state-of-the-art autoregressive ASR frameworks. In this paper, we propose various approaches to boosting the performance of a CTC-mask-based nonautoregressive Transformer under code-switching ASR scenario. To begin with, we attempt diversified masking method that are closely related with code-switching point, yielding an improved baseline model. More importantly, we employ MinimumWord Error (MWE) criterion to train the model. One of the challenges is how to generate a diversified hypothetical space, so as to obtain the average loss for a given ground truth. To address such a challenge, we explore different approaches to yielding desired N-best-based hypothetical space. We demonstrate the efficacy of the proposed methods on SEAME corpus, a challenging English-Mandarin code-switching corpus for Southeast Asia community. Compared with the crossentropy-trained strong baseline, the proposed MWE training method achieves consistent performance improvement on the test sets.

eess.AS↗

arXiv2021

Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization

In this paper, we examine the use of Transfer Learning using Pretrained Audio Neural Networks (PANNs), and propose an architecture that is able to better leverage the acoustic features provided by PANNs for the Automated Audio Captioning Task. We also introduce a novel self-supervised objective, Reconstruction Latent Space Similarity Regularization (RLSSR). The RLSSR module supplements the training of the model by minimizing the similarity between the encoder and decoder embedding. The combination of both methods allows us to surpass state of the art results by a significant margin on the Clotho dataset across several metrics and benchmarks.

cs.CL↗

arXiv2021

Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the back-end in this paper. One of the advantage of the proposed method is that the entire system can be trained from scratch. Different from prior works, either component here doesn't need to perform pre-training and fine-tuning processes separately. Through analysis, we found that the success of the proposed method lies in the following aspects. Firstly, multitask learning is essential, that is the SE network is not only learning to produce more Intelligent speech, it is also aimed to generate speech that is beneficial to recognition. Secondly, we also found speech phase preserved from noisy speech is critical for improving ASR performance. Thirdly, we propose a dual channel data augmentation training method to obtain further improvement.Specifically, we combine the clean and enhanced speech to train the whole system. We evaluate the proposed method on the RATS English data set, achieving a relative WER reduction of 4.6% with the joint training method, and up to a relative WER reduction of 11.2% with the proposed data augmentation method.

eess.AS↗

arXiv2021

E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition

In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable or even better results than standalone systems. Specifically, we found that the overall performance is predominantly determined by the ASR task, and the E2E-based ASR pretraining is essential to achieve improved performance, particularly for the AR task. Additionally, we conduct several analyses of the proposed method. First, though the objective loss for the AR task is much smaller compared with its counterpart of ASR task, a smaller weighting factor with the AR task in the joint objective function is necessary to yield better results for each task. Second, we found that sharing only a few layers of the encoder yields better AR results than sharing the overall encoder. Experimentally, the proposed method produces WER results close to the best standalone E2E ASR ones, while it achieves 7.7% and 4.2% relative improvement over standalone and single-task-based joint recognition methods on test set for accent recognition respectively.

eess.AS↗

arXiv2021

Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework

Human can recognize speech, as well as the peculiar accent of the speech simultaneously. However, present state-of-the-art ASR system can rarely do that. In this paper, we propose a multilingual approach to recognizing English speech, and related accent that speaker conveys using DNN-HMM framework. Specifically, we assume different accents of English as different languages. We then merge them together and train a multilingual ASR system. During decoding, we conduct two experiments. One is a monolingual ASR-based decoding, with the accent information embedded at phone level, realizing word-based accent recognition (AR), and the other is a multilingual ASR-based decoding, realizing an approximated utterance-based AR. Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy. Besides, we conduct extensive analysis for the proposed method, such as transfer learning without-domain data exploitation, cross-accent recognition confusion, as well as characteristics of accented-word.

eess.AS↗

arXiv2021

Multi-stage Speaker Extraction with Utterance and Frame-Level Reference Signals

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted speech in early stages is used as the reference speech for late stages. For the first time, we use frame-level sequential speech embedding as the reference for target speaker. This is a departure from the traditional utterance-based speaker embedding reference. In addition, a signal fusion scheme is proposed to combine the decoded signals in multiple scales with automatically learned weights. Experiments on WSJ0-2mix and its noisy versions (WHAM! and WHAMR!) show that SpEx++ consistently outperforms other state-of-the-art baselines.

eess.AS↗

arXiv2021

End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN

Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified context vector which takes into account total attention across encoder units as well, giving us a new cross-attention mechanism. Apart from this, we also investigate a multi-task learning approach for jointly estimating speaker height and age. We train and test our model on the TIMIT corpus. Our model outperforms several approaches in the literature. We achieve a root mean square error (RMSE) of 6.92cm and6.34cm for male and female heights respectively and RMSE of 7.85years and 8.75years for male and females ages respectively. By tracking the attention weights allocated to different phones, we find that Vowel phones are most important whistlestop phones are least important for the estimation task.

cs.SD↗

arXiv2020

GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a dialogue. When the given text is long, it is challenging to identify indicative words for the relation prediction. Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence. In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. We then refine this graph to select important words for relation prediction. Finally, the representation of the refined graph and the BERT-based sequence representation are concatenated for relation extraction. Specifically, in our proposed GDPNet (Gaussian Dynamic Time Warping Pooling Net), we utilize Gaussian Graph Generator (GGG) to generate edges of the multi-view graph. The graph is then refined by Dynamic Time Warping Pooling (DTWPool). On DialogRE and TACRED, we show that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence-level RE.

cs.CL↗

arXiv2020

Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance

Automatic speech recognition (ASR) for under-represented named-entity (UR-NE) is challenging due to such named-entities (NE) have insufficient instances and poor contextual coverage in the training data to learn reliable estimates and representations. In this paper, we propose approaches to enriching UR-NEs to improve speech recognition performance. Specifically, our first priority is to ensure those UR-NEs to appear in the word lattice if there is any. To this end, we make exemplar utterances for those UR-NEs according to their categories (e.g. location, person, organization, etc.), ending up with an improved language model (LM) that boosts the UR-NE occurrence in the word lattice. With more UR-NEs appearing in the lattice, we then boost the recognition performance through lattice rescoring methods. We first enrich the representations of UR-NEs in a pre-trained recurrent neural network LM (RNNLM) by borrowing the embedding representations of the rich-represented NEs (RR-NEs), yielding the lattices that statistically favor the UR-NEs. Finally, we directly boost the likelihood scores of the utterances containing UR-NEs and gain further performance improvement.

cs.SD↗

arXiv2020

Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, our models are able to achieve state-of-the-art results on the English all-words benchmark datasets.

cs.CL↗

arXiv2020

Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition

In this paper, we conduct data selection analysis in building an English-Mandarin code-switching (CS) speech recognition (CSSR) system, which is aimed for a real CSSR contest in China. The overall training sets have three subsets, i.e., a code-switching data set, an English (LibriSpeech) and a Mandarin data set respectively. The code-switching data are Mandarin dominated. First of all, it is found using the overall data yields worse results, and hence data selection study is necessary. Then to exploit monolingual data, we find data matching is crucial. Mandarin data is closely matched with the Mandarin part in the code-switching data, while English data is not. However, Mandarin data only helps on those utterances that are significantly Mandarin-dominated. Besides, there is a balance point, over which more monolingual data will divert the CSSR system, degrading results. Finally, we analyze the effectiveness of combining monolingual data to train a CSSR system with the HMM-DNN hybrid framework. The CSSR system can perform within-utterance code-switch recognition, but it still has a margin with the one trained on code-switching data.

eess.AS↗

arXiv2020

SpEx+: A Complete Time Domain Speaker Extraction Network

Speaker extraction aims to extract the target speech signal from a multi-talker environment given a target speaker's reference speech. We recently proposed a time-domain solution, SpEx, that avoids the phase estimation in frequency-domain approaches. Unfortunately, SpEx is not fully a time-domain solution since it performs time-domain speech encoding for speaker extraction, while taking frequency-domain speaker embedding as the reference. The size of the analysis window for time-domain and the size for frequency-domain input are also different. Such mismatch has an adverse effect on the system performance. To eliminate such mismatch, we propose a complete time-domain speaker extraction solution, that is called SpEx+. Specifically, we tie the weights of two identical speech encoder networks, one for the encoder-extractor-decoder pipeline, another as part of the speaker encoder. Experiments show that the SpEx+ achieves 0.8dB and 2.1dB SDR improvement over the state-of-the-art SpEx baseline, under different and same gender conditions on WSJ0-2mix-extr database respectively.

eess.AS↗

arXiv2020

Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning

In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture. This architecture not only takes advantage of the highly effective encoding capacity of the Transformer network but also benefits from extra text data due to the LSTM-based independent language model network. We conduct experiments on our in-house Malay corpus which contains limited labeled data and a large amount of extra text. Results show that the proposed architecture outperforms the previous LSTM-based architecture [1] by 24.2% relative word error rate (WER) when both are trained using limited labeled data. Starting from this, we obtain further 25.4% relative WER reduction by transfer learning from another resource-rich language. Moreover, we obtain additional 13.6% relative WER reduction by boosting the LSTM decoder of the transferred model with the extra text data. Overall, our best model outperforms the vanilla Transformer ASR by 11.9% relative WER. Last but not least, the proposed hybrid architecture offers much faster inference compared to both LSTM and Transformer architectures.

eess.AS↗

arXiv2020

Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems

In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to rare or out-of-vocabulary (OOV) words in the training data, and thereby can't be modeled reliably. We begin with graphemic lexicon which allows to drop the necessity of phonetic models in hybrid ASR. We study it under different settings and demonstrate its effectiveness in dealing with underrepresented NEs. Next, we study the impact of neural language model (LM) with letter-based features derived to handle infrequent words. After that, we attempt to enrich representations of underrepresented NEs in pretrained neural LM by borrowing the embedding representations of rich-represented words. This let us gain significant performance improvement on underrepresented NE recognition. Finally, we boost the likelihood scores of utterances containing NEs in the word lattices rescored by neural LMs and gain further performance improvement. The combination of the aforementioned approaches improves NE recognition by up to 42% relatively.

eess.AS↗