Speech

2023-12-26 更新

A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder

Authors:Yang Xiang, Jingguang Tian, Xinhui Hu, Xinkang Xu, ZhaoHui Yin

Generally, the performance of deep neural networks (DNNs) heavily depends on the quality of data representation learning. Our preliminary work has emphasized the significance of deep representation learning (DRL) in the context of speech enhancement (SE) applications. Specifically, our initial SE algorithm employed a gated recurrent unit variational autoencoder (VAE) with a Gaussian distribution to enhance the performance of certain existing SE systems. Building upon our preliminary framework, this paper introduces a novel approach for SE using deep complex convolutional recurrent networks with a VAE (DCCRN-VAE). DCCRN-VAE assumes that the latent variables of signals follow complex Gaussian distributions that are modeled by DCCRN, as these distributions can better capture the behaviors of complex signals. Additionally, we propose the application of a residual loss in DCCRN-VAE to further improve the quality of the enhanced speech. {Compared to our preliminary work, DCCRN-VAE introduces a more sophisticated DCCRN structure and probability distribution for DRL. Furthermore, in comparison to DCCRN, DCCRN-VAE employs a more advanced DRL strategy. The experimental results demonstrate that the proposed SE algorithm outperforms both our preliminary SE framework and the state-of-the-art DCCRN SE method in terms of scale-invariant signal-to-distortion ratio, speech quality, and speech intelligibility.
PDF Accepted by ICASSP 2024

点此查看论文截图

SELM: Speech Enhancement Using Discrete Tokens and Language Models

Authors:Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv, Ning Jiang, Guoqing Zhao, Lei Xie

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information holds potential advantages for speech enhancement tasks. In light of this, we propose SELM, a novel paradigm for speech enhancement, which integrates discrete tokens and leverages language models. SELM comprises three stages: encoding, modeling, and decoding. We transform continuous waveform signals into discrete tokens using pre-trained self-supervised learning (SSL) models and a k-means tokenizer. Language models then capture comprehensive contextual information within these tokens. Finally, a detokenizer and HiFi-GAN restore them into enhanced speech. Experimental results demonstrate that SELM achieves comparable performance in objective metrics alongside superior results in subjective perception. Our demos are available https://honee-w.github.io/SELM/.
PDF 5 pages, 2 figures. ACCEPTED BY ICASSP 2024

点此查看论文截图

Efficiency-oriented approaches for self-supervised speech representation learning

Authors:Luis Lugo, Valentin Vielzeuf

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and speech. In particular, the state-of-the-art in several speech processing applications, such as automatic speech recognition or speaker identification, are models where the latent representation is learned using self-supervised approaches. Several configurations exist in self-supervised learning for speech, including contrastive, predictive, and multilingual approaches. There is, however, a crucial limitation in most existing approaches: their high computational costs. These costs limit the deployment of models, the size of the training dataset, and the number of research groups that can afford research with large self-supervised models. Likewise, we should consider the environmental costs that high energy consumption implies. Efforts in this direction comprise optimization of existing models, neural architecture efficiency, improvements in finetuning for speech processing tasks, and data efficiency. But despite current efforts, more work could be done to address high computational costs in self-supervised representation learning.
PDF 16 pages, 3 figures

点此查看论文截图

A Refining Underlying Information Framework for Speech Enhancement

Authors:Rui Cao, Tianrui Wang, Meng Ge, Longbiao Wang, Jianwu Dang

The advent of deep neural networks (DNN) has significantly improved the performance of monaural speech enhancement (SE). Most of them attempt to implicitly capture the structural features of speech through distribution approximation. However, existing methods are susceptible to the issues of degraded speech and residual noise. This letter is grounded in the Information Bottleneck as an anchor to rethink the SE. By defining the incremental convergence of mutual information between speech characteristics, we elucidate that the acoustic characteristic of speech is crucial in alleviating the above issues, for its explicit introduction contributes to further approximating the optimal information-theoretic upper bound of the optimization. Referring to the chain rule of entropy, we also propose a framework to reconstruct the information composition of the optimization objective, aiming to integrate and refine this underlying characteristic without loss of generality. The visualization reflects consistency with analysis using information theory. Experimental results show that with only 1.18 M additional parameters, the refined CRN has yielded substantial progress over a number of advanced methods. The source code is available at https://github.com/caoruitju/RUI_SE.
PDF 5 pages

点此查看论文截图

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling

Authors:Rui Liu, Yifan Hu, Yi Ren, Xiang Yin, Haizhou Li

Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not thoroughly investigated the emotional expressiveness problems due to the scarcity of emotional conversational datasets and the difficulty of stateful emotion modeling. In this paper, we propose a novel emotional CSS model, termed ECSS, that includes two main components: 1) to enhance emotion understanding, we introduce a heterogeneous graph-based emotional context modeling mechanism, which takes the multi-source dialogue history as input to model the dialogue context and learn the emotion cues from the context; 2) to achieve emotion rendering, we employ a contrastive learning-based emotion renderer module to infer the accurate emotion style for the target utterance. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity, and annotate additional emotional information on the existing conversational dataset (DailyTalk). Both objective and subjective evaluations suggest that our model outperforms the baseline models in understanding and rendering emotions. These evaluations also underscore the importance of comprehensive emotional annotations. Code and audio samples can be found at: https://github.com/walker-hyf/ECSS.
PDF 9 pages, 4 figures, Accepted by AAAI’2024, Code and audio samples: https://github.com/walker-hyf/ECSS

点此查看论文截图

On real-time multi-stage speech enhancement systems

Authors:Lingjun Meng, Jozef Coldenhoff, Paul Kendrick, Tijana Stojkovic, Andrew Harper, Kiril Ratmanski, Milos Cernak

Recently, multi-stage systems have stood out among deep learning-based speech enhancement methods. However, these systems are always high in complexity, requiring millions of parameters and powerful computational resources, which limits their application for real-time processing in low-power devices. Besides, the contribution of various influencing factors to the success of multi-stage systems remains unclear, which presents challenges to reduce the size of these systems. In this paper, we extensively investigate a lightweight two-stage network with only 560k total parameters. It consists of a Mel-scale magnitude masking model in the first stage and a complex spectrum mapping model in the second stage. We first provide a consolidated view of the roles of gain power factor, post-filter, and training labels for the Mel-scale masking model. Then, we explore several training schemes for the two-stage network and provide some insights into the superiority of the two-stage network. We show that the proposed two-stage network trained by an optimal scheme achieves a performance similar to a four times larger open source model DeepFilterNet2.
PDF To appear at ICASSP 2024

点此查看论文截图

Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models

Authors:Atsunori Ogawa, Naohiro Tawara, Marc Delcroix, Shoko Araki

We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectiveness of combining a small number of NLMs. In contrast, in this study, we combine up to eight NLMs, i.e., forward/backward long short-term memory/Transformer-LMs that are trained with two different random initialization seeds. We combine these NLMs through iterative lattice generation. Since these NLMs work complementarily with each other, by combining them one by one at each rescoring iteration, language scores attached to given lattice arcs can be gradually refined. Consequently, errors of the ASR hypotheses can be gradually reduced. We also investigate the effectiveness of carrying over contextual information (previous rescoring results) across a lattice sequence of a long speech such as a lecture speech. In experiments using a lecture speech corpus, by combining the eight NLMs and using context carry-over, we obtained a 24.4% relative word error rate reduction from the ASR 1-best baseline. For further comparison, we performed simultaneous (i.e., non-iterative) NLM combination and 100-best rescoring using the large ensemble of NLMs, which confirmed the advantage of lattice rescoring with iterative NLM combination.
PDF Accepted to ICASSP 2022

点此查看论文截图

Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition

Authors:Ashish Seth, Sreyan Ghosh, S. Umesh, Dinesh Manocha

Continued self-supervised (SSL) pre-training for adapting existing SSL models to the target domain has shown to be extremely effective for low-resource Automatic Speech Recognition (ASR). This paper proposes Stable Distillation, a simple and novel approach for SSL-based continued pre-training that boosts ASR performance in the target domain where both labeled and unlabeled data are limited. Stable Distillation employs self-distillation as regularization for continued pre-training, alleviating the over-fitting issue, a common problem continued pre-training faces when the source and target domains differ. Specifically, first, we perform vanilla continued pre-training on an initial SSL pre-trained model on the target domain ASR dataset and call it the teacher. Next, we take the same initial pre-trained model as a student to perform continued pre-training while enforcing its hidden representations to be close to that of the teacher (via MSE loss). This student is then used for downstream ASR fine-tuning on the target dataset. In practice, Stable Distillation outperforms all our baselines by 0.8 - 7 WER when evaluated in various experimental settings.
PDF Accepted to ICASSP 2024. Code: https://github.com/cs20s030/stable_distillation

点此查看论文截图

HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments

Authors:Neeraj Kumar Singh, Koyel Ghosh, Joy Mahapatra, Utpal Garain, Apurbalal Senapati

Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate the intensity of hate speech. While studies have shown that context-level semantics are crucial for detecting hateful comments, most of this research focuses on English due to the ample datasets available. In contrast, low-resource languages, like Indian languages, remain under-researched because of limited datasets. Contrary to hate speech detection, hate intensity reduction remains unexplored in high-resource and low-resource languages. In this paper, we propose a novel end-to-end model, HCDIR, for Hate Context Detection, and Hate Intensity Reduction in social media posts. First, we fine-tuned several pre-trained language models to detect hateful comments to ascertain the best-performing hateful comments detection model. Then, we identified the contextual hateful words. Identification of such hateful words is justified through the state-of-the-art explainable learning model, i.e., Integrated Gradient (IG). Lastly, the Masked Language Modeling (MLM) model has been employed to capture domain-specific nuances to reduce hate intensity. We masked the 50\% hateful words of the comments identified as hateful and predicted the alternative words for these masked terms to generate convincing sentences. An optimal replacement for the original hate comments from the feasible sentences is preferred. Extensive experiments have been conducted on several recent datasets using automatic metric-based evaluation (BERTScore) and thorough human evaluation. To enhance the faithfulness in human evaluation, we arranged a group of three human annotators with varied expertise.
PDF

点此查看论文截图

A Strong Baseline for Temporal Video-Text Alignment

Authors:Zeqian Li, Qirui Chen, Tengda Han, Ya Zhang, Yanfeng Wang, Weidi Xie

In this paper, we consider the problem of temporally aligning the video and texts from instructional videos, specifically, given a long-term video, and associated text sentences, our goal is to determine their corresponding timestamps in the video. To this end, we establish a simple, yet strong model that adopts a Transformer-based architecture with all texts as queries, iteratively attending to the visual features, to infer the optimal timestamp. We conduct thorough experiments to investigate: (i) the effect of upgrading ASR systems to reduce errors from speech recognition, (ii) the effect of various visual-textual backbones, ranging from CLIP to S3D, to the more recent InternVideo, (iii) the effect of transforming noisy ASR transcripts into descriptive steps by prompting a large language model (LLM), to summarize the core activities within the ASR transcript as a new training dataset. As a result, our proposed simple model demonstrates superior performance on both narration alignment and procedural step grounding tasks, surpassing existing state-of-the-art methods by a significant margin on three public benchmarks, namely, 9.3% on HT-Step, 3.4% on HTM-Align and 4.7% on CrossTask. We believe the proposed model and dataset with descriptive steps can be treated as a strong baseline for future research in temporal video-text alignment. All codes, models, and the resulting dataset will be publicly released to the research community.
PDF

点此查看论文截图

BLSTM-Based Confidence Estimation for End-to-End Speech Recognition

Authors:Atsunori Ogawa, Naohiro Tawara, Takatomo Kano, Marc Delcroix

Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function for developing ASR applications. In this study, we perform confidence estimation for end-to-end (E2E) ASR hypotheses. Recent E2E ASR systems show high performance (e.g., around 5% token error rates) for various ASR tasks. In such situations, confidence estimation becomes difficult since we need to detect infrequent incorrect tokens from mostly correct token sequences. To tackle this imbalanced dataset problem, we employ a bidirectional long short-term memory (BLSTM)-based model as a strong binary-class (correct/incorrect) sequence labeler that is trained with a class balancing objective. We experimentally confirmed that, by utilizing several types of ASR decoding scores as its auxiliary features, the model steadily shows high confidence estimation performance under highly imbalanced settings. We also confirmed that the BLSTM-based model outperforms Transformer-based confidence estimation models, which greatly underestimate incorrect tokens.
PDF Accepted to ICASSP 2021

点此查看论文截图