We present the IMS-Speech, a web based tool for German and English speech transcription aiming to facilitate research in various disciplines which require accesses to lexical information in spoken language materials. This tool is based on modern open source software stack, advanced speech recognition methods and public data resources and is freely available for academic researchers. The utilized models are built to be generic in order to provide transcriptions of competitive accuracy on a diverse set of tasks and conditions.
Institute for Natural Language Processing, University of Stuttgart（斯图加特大学自然语言处理研究所）
This paper describes the submission to the IWSLT 2021 Low-Resource Speech Translation Shared Task by IMS team. We utilize state-of-the-art models combined with several data augmentation, multi-task and transfer learning approaches for the automatic speech recognition (ASR) and machine translation (MT) steps of our cascaded system. Moreover, we also explore the feasibility of a full end-to-end speech translation (ST) model in the case of very constrained amount of ground truth labeled data. Our best system achieves the best performance among all submitted systems for Congolese Swahili to Englis…
This paper proposes Virtuoso, a massively multilingual speech-text joint semi-supervised learning framework for text-to-speech synthesis (TTS) models. Existing multilingual TTS typically supports tens of languages, which are a small fraction of the thousands of languages in the world. One difficulty to scale multilingual TTS to hundreds of languages is collecting high-quality speech-text paired data in low-resource languages. This study extends Maestro, a speech-text joint pretraining framework for automatic speech recognition (ASR), to speech generation tasks. To train a TTS model from variou…
National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discre…
University of Waterloo（滑铁卢大学）；Baidu Research USA（百度美国研究院）；Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation. However, all the above tasks are in the direction of speech understanding, but for the inverse direction, speech synthesis, the potential of representation learning is yet to be realized, due to the challenging nature of generating high-quality speech. To address this problem, we propose our framework, Alignment-Aware Acoustic-Text Pretraining (A$^3$T), which reconstructs masked acoustic signals with text input and acoustic-text alig…
Nowadays, the main problem of deep learning techniques used in the development of automatic speech recognition (ASR) models is the lack of transcribed data. The goal of this research is to propose a new data augmentation method to improve ASR models for agglutinative and low-resource languages. This novel data augmentation method generates both synthetic text and synthetic audio. Some experiments were conducted using the corpus of the Quechua language, which is an agglutinative and low-resource language. In this study, a sequence-to-sequence (seq2seq) model was applied to generate synthetic te…
Direct speech-to-speech translation (S2ST) is among the most challenging problems in the translation paradigm due to the significant scarcity of S2ST data. While effort has been made to increase the data size from unlabeled speech by cascading pretrained speech recognition (ASR), machine translation (MT) and text-to-speech (TTS) models; unlabeled text has remained relatively under-utilized to improve S2ST. We propose an effective way to utilize the massive existing unlabeled text from different languages to create a large amount of S2ST data to improve S2ST performance by applying various acou…
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data. However, the lack of aligned data poses a major practical problem for TTS and ASR on low-resource languages. In this paper, by leveraging the dual nature of the two tasks, we propose an almost unsupervised learning method that only leverages few hundreds of paired data and extra unpaired data for TTS and ASR. Our method consists of the following components: (1) …
DiappyMed；EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Alès（EuroMov数字健康运动实验室，蒙彼利埃大学，IMT阿莱斯矿业学院）
This study presents a large scale benchmarking on cloud based Speech-To-Text systems: {Google Cloud Speech-To-Text}, {Microsoft Azure Cognitive Services}, {Amazon Transcribe}, {IBM Watson Speech to Text}. For each systems, 40158 clean and noisy speech files about 101 hours are tested. Effect of background noise on STT quality is also evaluated with 5 different Signal-to-noise ratios from 40dB to 0dB. Results showed that {Microsoft Azure} provided lowest transcription error rate $9.09\%$ on clean speech, with high robustness to noisy environment. {Google Cloud} and {Amazon Transcribe} gave simi…
Training state-of-the-art Automated Speech Recognition (ASR) models typically requires a substantial amount of transcribed speech. In this work, we demonstrate that a modality-matched joint speech and text model can be leveraged to train a massively multilingual ASR model without any supervised (manually transcribed) speech for some languages. This paper explores the use of jointly learnt speech and text representations in a massively multilingual, zero supervised speech, real-world setting to expand the set of languages covered by ASR with only unlabeled speech and text in the target language…
Carnegie Mellon University（卡内基梅隆大学）；National Taiwan University（台湾大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Meta AI
Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown reasonable improvements to various SLU tasks. However, because of the mismatched modalities between speech signals and text tokens, previous methods usually need complex designs of the frameworks. This work proposes a simple yet efficient unsupervised paradigm that connects speech and textual pre-trained models, resulting in an unsupervised speech-to-semantic pre-tr…
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
Hong Kong University of Science and Technology, Hong Kong SAR（香港理工大学）；Tencent, China（腾讯）；University of Surrey, United Kingdom（Surrey大学）；Chinese University of Hong Kong, Hong Kong SAR（香港中文大学）；Hong Kong Baptist University, Hong Kong SAR（香港 Baptist大学）；Hong Kong Polytechnic University, Hong Kong SAR（香港理工大学）；Independent Researcher（独立研究者）
Brno University of Technology（布尔诺理工大学）；Sharif DeepMine Ltd.（谢里夫DeepMine有限公司）
DeepMine is a speech database in Persian and English designed to build and evaluate text-dependent, text-prompted, and text-independent speaker verification, as well as Persian speech recognition systems. It contains more than 1850 speakers and 540 thousand recordings overall, more than 480 hours of speech are transcribed. It is the first public large-scale speaker verification database in Persian, the largest public text-dependent and text-prompted speaker verification database in English, and the largest public evaluation dataset for text-independent speaker verification. It has a good cover…
Xinjiang University（新疆大学）；Bytedance AI Lab（字节跳动人工智能实验室）；Nanyang Technological University（南洋理工大学）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders. In this paper we propose to employ a novel bidirectional attention mechanism (BiAM) to jointly learn both ASR encoder (bottom layers) and text encoder with a multi-modal learning method. The BiAM is to facilitate feature sampling rate exchange, realizing the quality …
University of Science and Technology of China（中国科学技术大学）；Microsoft（微软）；Microsoft Research Asia（微软亚洲研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Leveraging hidden-unit as an interface to align speech and text, we can decompose the speech-to-text model into a speech-to-unit model and a unit-to-text model, which can be jointly pre-trained with unpaired speech and text data respectively. Our proposed SpeechUT is fine-tuned…
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality differences between speech outputs from the encoder and text inputs to the decoder. In this work, we aim to bridge the modality gap between speech and text to improve translation quality. We propose M-Adapter, a novel Transformer-based module, to adapt speech representations to text. While shrinking the speech sequence, M-Adapter produces features desired for sp…
Southern University of Science and Technology（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Tongji University（同济大学）；Microsoft（微软）；Peng Cheng Laboratory（鹏城实验室）
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text mod…
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…
Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for downstream speech tasks such as ASR. However, the distinct pre-training objectives make it challenging to jointly optimize the speech and text representation in the same model. To solve this problem, we propose Text-Enhanced Self-Supervised Speech Pre-training (TESSP), aiming to incorporate the linguistic information into speech pre-training. Our model consists o…
End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as sp…
We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to traditional cascaded systems and end-to-end architectures, our system does not require any labeled data (i.e., transcribed source audio or parallel source and target text corpora) during training, making it especially applicable to language pairs with very few or even zero bilingual resources. The framework initializes the ST system with a cross-modal biling…
Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation
Barcelona Supercomputing Center, Spain（巴塞罗那超级计算中心）；Universitat Politècnica de Catalunya, Spain（加泰罗尼亚理工大学）；DFKI GmbH, Saarland Informatics Campus, Saarbrücken, Germany（DFKI GmbH萨尔兰信息技术校区）
In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phonem…
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）
Existing speech to speech translation systems heavily rely on the text of target language: they usually translate source language either to target text and then synthesize target speech from text, or directly to target speech with target text for auxiliary training. However, those methods cannot be applied to unwritten target languages, which have no written text or phoneme available. In this paper, we develop a translation system for unwritten languages, named as UWSpeech, which converts target unwritten speech into discrete tokens with a converter, and then translates source-language speech …
Meta - Fundamental AI Research (FAIR)（Meta 基础人工智能研究院（FAIR））；Johns Hopkins University（约翰斯·霍普金斯大学）
We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or t…
Research Institute for Artificial Intelligence “Mihai Draganescu”, Romanian Academy（罗马尼亚科学院“米哈伊·德勒格内斯库”人工智能研究所）
In this paper we introduce a set of resources and tools aimed at providing support for natural language processing, text-to-speech synthesis and speech recognition for Romanian. While the tools are general purpose and can be used for any language (we successfully trained our system for more than 50 languages and participated in the Universal Dependencies Shared Task), the resources are only relevant for Romanian language processing.
We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-trainin…
This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into utterance-wise pairs of speech and text. Unlike conventional methods based on frame-synchronous prediction, the proposed method re-defines the speech-to-text alignment as a label-synchronous text mapping problem. This enables an accurate alignment benefiting from the strong inference ability of the state-of-the-art attention-based encoder-decoder models, which cannot…
University of California, Berkeley（加州大学伯克利分校）；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating increased data collection), and rapidly shifting data distributions (requiring more frequent model fine-tuning). In this work, we investigate the potential of leveraging external knowledge, particularly through off-policy key-value stores generated with text-to-speech methods, to allow for flexible post-training adaptation to new data distributions. In our approach,…
Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data. This presents a challenge for speech applications where labelled speech data is very expensive to obtain, such as automatic speech recognition (ASR) and speech translation (ST). In this study, we propose a general multi-task learning framework to leverage text data for ASR and ST tasks. Two auxiliary tasks, a denoising autoencoder task and machine translati…
Speech recognition has of late become a practical technology for real world applications. Aiming at speech-driven text retrieval, which facilitates retrieving information with spoken queries, we propose a method to integrate speech recognition and retrieval methods. Since users speak contents related to a target collection, we adapt statistical language models used for speech recognition based on the target collection, so as to improve both the recognition and retrieval accuracy. Experiments using existing test collections combined with dictated queries showed the effectiveness of our method.
University of Edinburgh（爱丁堡大学）；Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations. We present the first system for this problem applied to a realistic multi-speaker dataset, the CALLHOME Spanish-English speech translation corpus. Our approach uses unsupervised term discovery (UTD) to cluster repeated patterns in the audio, creating a pseudotext, which we pair with translations to create a parallel text and train a simple bag-of-w…
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a framework to achieve unsupervised ASR on a read English speech dataset, where audio and text are unaligned. In the first stage, each word-level audio segment in the utterances is represented by a vector representation extracted by a sequence-of-sequence autoencoder, in which phonetic information and speaker information are disentangled. Secondly, semantic embeddings…
End-to-end Speech Recognition with similar length speech and text
College of Computer Science and Cyber Security, Chengdu University of Technology（计算机科学与网络安全学院，成都理工大学）；National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University（合成视觉基础科学国家重点实验室，四川大学）
Radboud University（拉德堡德大学）；National University of Singapore（新加坡国立大学）
In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio broadcasts where one of the mixed languages, namely Frisian, is an under-resourced language. In previous work, we have proposed several automatic transcription strategies for CS speech to increase the amount of available training speech data. In this work, we explore how the acoustic modeling (AM) can benefit from monolingual speech data belonging to the high-resour…
