本文提出 BERT-CTC 和 BECTRA 两种模型，将预训练掩码语言模型 BERT 有效融入端到端语音识别，通过迭代细化与适配 ASR 的词汇表弥合文本差异，在多个 ASR 任务上优于 CTC 和 transducer 基线。
摘要：
我们提出了一种新颖的端到端自动语音识别（ASR）方法，该方法利用预训练的掩码语言模型（LMs）来促进语言信息的提取。所提出的模型 BERT-CTC 和 BECTRA 专门设计用于将预训练语言模型（例如 BERT）有效集成到端到端 ASR 模型中。BERT-CTC 通过解决输出标记之间条件独立性假设的约束，使 BERT 适应连接主义时间分类（CTC）。这使得在 ASR 过程中能够显式地以 BERT 的上下文嵌入为条件，并通过迭代细化算法无缝融合音频和语言信息。BECTRA 将 BERT-CTC 扩展到 transducer 框架，并使用适合 ASR 训练的词汇表训练解码器网络。这旨在弥合端到端 ASR 中处理的文本与 BERT 之间的差距，因为这些模型具有不同的词汇表以及不同的文本格式和风格，例如标点符号的存在。在各种 ASR 任务上的实验结果表明，由于引入了 BERT 知识，所提出的模型相对于基于 CTC 和 transducer 的基线均有所改进。此外，我们的深入分析和研究验证了所提出的公式和架构设计的有效性。
英文摘要：
We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are specifically designed to effectively integrate pre-trained LMs (e.g., BERT) into end-to-end ASR models. BERT-CTC adapts BERT for connectionist temporal classification (CTC) by addressing the constraint of the conditional independence assumption between output tokens. This enables explicit conditioning of BERT's contextualized embeddings in the ASR process, seamlessly merging audio and linguistic information through an iterative refinement algorithm. BECTRA extends BERT-CTC to the transducer framework and trains the decoder network using a vocabulary suitable for ASR training. This aims to bridge the gap between the text processed in end-to-end ASR and BERT, as these models have distinct vocabularies with varying text formats and styles, such as the presence of punctuation. Experimental results on various ASR tasks demonstrate that the proposed models improve over both the CTC and transducer-based baselines, owing to the incorporation of BERT knowledge. Moreover, our in-depth analysis and investigation verify the effectiveness of the proposed formulations and architectural designs.
Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline single-talker applications, with limited investigations in multi-talker cases, especially for streaming scenarios. In this paper, we investigate SSL for streaming multi-talker speech recognition, which generates transcriptions of overlapping speakers in a streaming fashion. We first observe that conventional SSL techniques do not work well on this task due to the poor…
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance and also the pre-training efficiency, either through decoding with a hybrid ASR system to generate phoneme-level alignments (named PBERT), or performing clustering on the supervised speech features extracted from an end-to-end CTC mo…
Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of speech quality (PESQ), does not necessarily lead to improved speech recognition performance due to speech distortion in the enhancement stage. In this paper, a multi-channel dilated convolutional network based frequency domain modeling is presented to enhance target speaker in the far-field, noisy and multi-talker conditions. We study three approaches towards …
Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation. In this paper, we proposed to use a predicted loss that estimates the uncertainty of the sample. The CTC (Connectionist Temporal Classification) and attention loss are informative for speech recognition since they are computed based on all decoding paths and alignments. We defined an end-to-end active learning pipeline, training an ASR/LP (Automatic Speech Re…
Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems, they have one major limitation. They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations. In this work, we address this limitation. We propose ask2mask (ATM), a novel approach to focus on specific samples during MSM pre-training. ATM employs an exter…
Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-train…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Meta AI
Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT (AV-HuBERT), a self-supervised representation learning framework for audio-visual speech, which masks multi-stream video input and predicts automatically discovered and iteratively refined multimodal hidden units. AV-HuBERT learns powerful audio-visual speech representation benefiting both lip-reading and automatic speech recognition. On the largest public lip-…
In this paper, we describe our submissions to the ZeroSpeech 2021 Challenge and SUPERB benchmark. Our submissions are based on the recently proposed FaST-VGS model, which is a Transformer-based model that learns to associate raw speech waveforms with semantically related images, all without the use of any transcriptions of the speech. Additionally, we introduce a novel extension of this model, FaST-VGS+, which is learned in a multi-task fashion with a masked language modeling objective in addition to the visual grounding objective. On ZeroSpeech 2021, we show that our models perform competitiv…
Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applyin…
Seasalt AI LLC（海盐人工智能有限责任公司）；Xiaoice, Microsoft Corporation（微软公司小冰团队）；Xiaomi Corporation（小米公司）
This paper presents the "Ethiopian" system for the SLT 2021 Children Speech Recognition Challenge. Various data processing and augmentation techniques are proposed to tackle children's speech recognition problem, especially the lack of the children's speech recognition training data issue. Detailed experiments are designed and conducted to show the effectiveness of each technique, across different speech recognition toolkits and model architectures. Step by step, we explain how we come up with our final system, which provides the state-of-the-art results in the SLT 2021 Children Speech Recogni…
Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses the recently successful self-supervised learning (SSL) methods to leverage many unlabeled speech data without CS. We show that hidden representations of SSL models offer frame-level language identity even if the models are trained with English speech only. Jointly training CTC and language identification modules with self-supervised speech representations i…
A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech. Notably, this includes the rapidly advancing neural network based end-to-end speech recognition systems. Children speech recognition is more challenging due to the larger intra-inter speaker variability in terms of acoustic and linguistic characteristics compared to adult speech. Furthermore, the lack of adequate and appropriate children speech resources adds to the challenge of designing robust end-to-end neural architectures. This study provides a critical asse…
We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation mode…
In their everyday life, the speech recognition performance of human listeners is influenced by diverse factors, such as the acoustic environment, the talker and listener positions, possibly impaired hearing, and optional hearing devices. Prediction models come closer to considering all required factors simultaneously to predict the individual speech recognition performance in complex acoustic environments. While such predictions may still not be sufficiently accurate for serious applications, they can already be performed and demand an accessible representation. In this contribution, an intera…
We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''. We generate targets for the sentiment classification using text-to-sentiment model trained on publicly available data. Finally, we fine-tune the acoustic ASR on emotion annotated speech data. We evaluated the proposed approach on the MSP-Podcast dataset, where we achieved the best reported concordance correlation coefficient (CCC) of 0.41 for v…
VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
National Engineering Research Center of Speech and Language Information Processing（国家语音及语言信息处理工程技术研究中心）；University of Science and Technology of China（中国科学技术大学）；Microsoft Corporation（微软公司）
Tomsk State University of Control Systems and Radioelectronics（托木斯克国立控制系统与无线电电子大学）
Distinctive features of the created speech frame are: the ability to take into account the emotional state of the speaker, sup-port for working with diseases of the speech-forming tract of speakers and the presence of manual segmentation of a num-ber of speech signals. In addition, the system is focused on Russian-language speech material, unlike most analogs.
Robust speech recognition is a key prerequisite for semantic feature extraction in automatic aphasic speech analysis. However, standard one-size-fits-all automatic speech recognition models perform poorly when applied to aphasic speech. One reason for this is the wide range of speech intelligibility due to different levels of severity (i.e., higher severity lends itself to less intelligible speech). To address this, we propose a novel acoustic model based on a mixture of experts (MoE), which handles the varying intelligibility stages present in aphasic speech by explicitly defining severity-ba…
The decade from 2010 to 2020 saw remarkable improvements in automatic speech recognition. Many people now use speech recognition on a daily basis, for example to perform voice search queries, send text messages, and interact with voice assistants like Amazon Alexa and Siri by Apple. Before 2010 most people rarely used speech recognition. Given the remarkable changes in the state of speech recognition over the previous decade, what can we expect over the coming decade? I attempt to forecast the state of speech recognition research and applications by the year 2030. While the changes to general …
This paper describes LeVoice automatic speech recognition systems to track2 of intelligent cockpit speech recognition challenge 2022. Track2 is a speech recognition task without limits on the scope of model size. Our main points include deep learning based speech enhancement, text-to-speech based speech generation, training data augmentation via various techniques and speech recognition model fusion. We compared and fused the hybrid architecture and two kinds of end-to-end architecture. For end-to-end modeling, we used models based on connectionist temporal classification/attention-based encod…
We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training (SOT) with attention-based encoder-decoder, a recently proposed method for recognizing overlapped speech comprising an arbitrary number of speakers. We extend SOT by introducing a speaker inventory as an auxiliary input to produce speaker labels as well as multi-speaker transcriptions. All model parameters are optimized by speaker-attributed maximum mutual info…
