The Zero Resource Speech Challenge 2021: Spoken language modelling
University of Toronto（多伦多大学）；Cognitive Machine Learning (ENS--CNRS--EHESS--INRIA--PSL Research University)（认知机器学习实验室（巴黎高等师范学院--法国国家科学研究中心--社会科学高等研究院--法国国家信息与自动化研究所--巴黎文理研究大学））；Facebook AI Research（脸书人工智能研究院）
Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Eugene Kharitonov, Emmanuel Dupoux
备注：
Submitted to Interspeech 2021. arXiv admin note: text overlap with arXiv:2011.11588
We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (acceptability judgment) and semantic levels (similarity judgment). We present an overview of the eight submitted systems from four groups and discuss the main results.
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
DAMO Academy, Alibaba Group（阿里巴巴集团大模型研究院）；Computer Science and Engineering Division, University of Michigan（密歇根大学计算机科学与工程系）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学光明人工智能学院）
This paper presents an augmentation of MSCOCO dataset where speech is added to image and text. Speech captions are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. Disfluencies and speed perturbation are added to the signal in order to sound more natural. Each speech signal (WAV) is paired with a JSON file containing exact timecode for each word/syllable/phoneme in the spoken caption. Such a corpus could be used for Language and Vision (LaVi) tasks including speech input or output instead of text. Investigating multimodal …
The majority of current Text-to-Speech (TTS) datasets, which are collections of individual utterances, contain few conversational aspects. In this paper, we introduce DailyTalk, a high-quality conversational speech dataset designed for conversational TTS. We sampled, modified, and recorded 2,541 dialogues from the open-domain dialogue dataset DailyDialog inheriting its annotated attributes. On top of our dataset, we extend prior work as our baseline, where a non-autoregressive TTS is conditioned on historical information in a dialogue. From the baseline experiment with both general and our nov…
The CMU Wilderness Multilingual Speech Dataset (Black, 2019) is a newly published multilingual speech dataset based on recorded readings of the New Testament. It provides data to build Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) models for potentially 700 languages. However, the fact that the source content (the Bible) is the same for all the languages is not exploited to date.Therefore, this article proposes to add multilingual links between speech segments in different languages, and shares a large and clean dataset of 8,130 parallel spoken utterances across 8 languages (56 l…
Toxic speech, also known as hate speech, is regarded as one of the crucial issues plaguing online social media today. Most recent work on toxic speech detection is constrained to the modality of text and written conversations with very limited work on toxicity detection from spoken utterances or using the modality of speech. In this paper, we introduce a new dataset DeToxy, the first publicly available toxicity annotated dataset for the English language. DeToxy is sourced from various openly available speech databases and consists of over 2 million utterances. We believe that our dataset would…
Facebook AI Research（Facebook人工智能研究院）；EHESS（社会科学高等学院）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot metrics probing for the quality of the learned models at 4 linguistic levels: phonetics, lexicon, syntax and semantics. We present the results and analyses of a composite baseline made of the concatenation of three unsupervised systems: self-supervised contrastive representation learning (CPC), clustering (k-means) and language modeling (LSTM or BERT). The langu…
Aalto University（阿尔托大学）；University of Helsinki（赫尔辛基大学）
The Donate Speech campaign has so far succeeded in gathering approximately 3600 hours of ordinary, colloquial Finnish speech into the Lahjoita puhetta (Donate Speech) corpus. The corpus includes over twenty thousand speakers from all the regions of Finland and from all age brackets. The primary goals of the collection were to create a representative, large-scale resource to study spontaneous spoken Finnish and to accelerate the development of language technology and speech-based services. In this paper, we present the collection process and the collected corpus, and showcase its versatility th…
In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on unsupervised induction of semantic representations of words, whole sentences and longer texts. In this study we examine the challenges of adapting these approaches from written to spoken language. We conjecture that unsupervised learning of the semantics of spoken language becomes feasible if we abstract from the surface variability. We simulate this setting with a dat…
Xi’an Jiaotong University（西安交通大学）；Delft University of Technology（代尔夫特理工大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper proposes a new model, referred to as the show and speak (SAS) model that, for the first time, is able to directly synthesize spoken descriptions of images, bypassing the need for any text or phonemes. The basic structure of SAS is an encoder-decoder architecture that takes an image as input and predicts the spectrogram of speech that describes this image. The final speech audio is obtained from the predicted spectrogram via WaveNet. Extensive experiments on the public benchmark database Flickr8k demonstrate that the proposed SAS is able to synthesize natural spoken descriptions for …
BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
LSCP；ENS（巴黎高等师范学院）；EHESS（高等社会科学研究学院）；CNRS（法国国家科学研究中心）；PSL University（PSL大学）；Meta AI Research（Meta人工智能研究院）；Tampere University（坦佩雷大学）；IRIT；INRIA（法国国家信息与自动化研究院）
Training end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains. One practical solution to the data scarcity issue is to convert machine translation data (MT) to ST data via text-to-speech (TTS) systems. Yet, using TTS systems can be tedious and slow, as the conversion needs to be done for each MT dataset. In this work, we propose a simple, scalable and effective data augmentation technique, i.e., SpokenVocab, to convert MT data to ST data on-the-fly. The idea is to retrieve and stitch audio snippets from a Sp…
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Alibaba Group（阿里巴巴集团）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
Columbia University（哥伦比亚大学）；Microsoft（微软）；Stanford University（斯坦福大学）
Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-trivial. Despite the pervasiveness of spoken dialog, automated speech understanding and quality information extraction remains markedly poor, especially when compared to written prose. Furthermore, compared to understanding text, auditory communication poses many additional challenges such as speaker disfluencies, informal prose styles, and lack of structure. These concerns all demonstrate the need for a distinctly spee…
Reading comprehension has been widely studied. One of the most representative reading comprehension tasks is Stanford Question Answering Dataset (SQuAD), on which machine is already comparable with human. On the other hand, accessing large collections of multimedia or spoken content is much more difficult and time-consuming than plain text content for humans. It's therefore highly attractive to develop machines which can automatically understand spoken content. In this paper, we propose a new listening comprehension task - Spoken SQuAD. On the new task, we found that speech recognition errors …
Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
Center For Artificial Intelligence and Data Science, University of Würzburg（人工智能与数据科学中心，乌尔姆大学）；Language Technology Lab, University of Cambridge（语言技术实验室，剑桥大学）；Mila, McGill University and Canada CIFAR AI Chair（Mila，麦吉尔大学及加拿大CIFAR人工智能主席）
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
Carnegie Mellon University（卡内基梅隆大学）；National Taiwan University（国立台湾大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Massachusetts Institute of Technology（麻省理工学院）
IIIT Delhi（德里印度理工学院）；BITS Pilani（皮拉尼比尔拉科学技术学院）；Adobe（奥多比公司）；SUNY at Buffalo（纽约州立大学布法罗分校）；Second Language Testing Inc（第二语言测试公司）；National University of Singapore（新加坡国立大学）
While there has been significant progress towards modelling coherence in written discourse, the work in modelling spoken discourse coherence has been quite limited. Unlike the coherence in text, coherence in spoken discourse is also dependent on the prosodic and acoustic patterns in speech. In this paper, we model coherence in spoken discourse with audio-based coherence models. We perform experiments with four coherence-related tasks with spoken discourses. In our experiments, we evaluate machine-generated speech against the speech delivered by expert human speakers. We also compare the spoken…
College of Electrical Engineering；Computer Science\ Taiwan University, Taiwan
Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work proposes to mitigate the ASR errors by aligning the mismatch between ASR hypotheses and their corresponding reference transcriptions. An adversarial model is applied to this domain adaptation task, which forces the model to learn domain-invariant features the QA model can effectively utilize in order to improve the SQA results. The experiments successfully demo…
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院）；Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems
Institute for Infocomm Research (I 2 R), A*STAR, Singapore（信息与通信研究 institute（I2R），A*STAR，新加坡）；Centre for Frontier AI Research (CFAR), A*STAR, Singapore（前沿人工智能研究 centre（CFAR），A*STAR，新加坡）
Khulna University of Engineering & Technology（库尔纳工程技术大学）
Speech recognition is a technique that converts human speech signals into text or words or in any form that can be easily understood by computers or other machines. There have been a few studies on Bangla digit recognition systems, the majority of which used small datasets with few variations in genders, ages, dialects, and other variables. Audio recordings of Bangladeshi people of various genders, ages, and dialects were used to create a large speech dataset of spoken '0-9' Bangla digits in this study. Here, 400 noisy and noise-free samples per digit have been recorded for creating the datase…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Microsoft Cognitive Services Group（微软认知服务组）
Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. However, the inherent disparities between the two modalities necessitate a mutual analysis. In this paper, we propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules. Besides conducting a self-supervised masked language modeling task on the …
In spoken question answering, QA systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations. Therefore, we propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling QA systems to model complex dialogues flow given the speech utterances and text corpora. In this task, our main objective is to build a QA system to deal with conversational questions both in spoken and text forms, and to explore the plausibility of providing m…
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Wuhan AI Research（武汉人工智能研究院）
Cognitive Systems Research Laboratory（认知系统研究实验室）；Tata Infotech Limited（塔塔信息技术有限公司）
The ability to classify spoken speech based on the style of speaking is an important problem. With the advent of BPO's in recent times, specifically those that cater to a population other than the local population, it has become necessary for BPO's to identify people with certain style of speaking (American, British etc). Today BPO's employ accent analysts to identify people having the required style of speaking. This process while involving human bias, it is becoming increasingly infeasible because of the high attrition rate in the BPO industry. In this paper, we propose a new metric, which r…
The Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system translates air travel (ATIS) queries from spoken English to spoken Swedish and to French. It is constructed, with as few modifications as possible, from existing pieces of speech and language processing software. The speech recognizer and language understander are connected by a fairly conventional pipelined N-best interface. This paper focuses on the ways in which the language processor makes intelligent use of the sente…
In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word using its contextual spoken word's speech and text, such that the model encodes its meaningful latent representations. Unlike existing work, we have used text along with speech for auditory representation learning to capture semantical and syntactical information along with the acoustic and temporal information. The lat…
LTCI, Telecom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；IBM GBS France（IBM全球企业服务法国分部）
While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.
FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences（智能信息处理重点实验室，计算技术研究所，中国科学院）；State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
In this paper, we have introduced and evaluated intonation based feature for scoring the English speech of nonnative English speakers in Indian context. For this, we created an automated spoken English scoring engine to learn from the manual evaluation of spoken English. This involved using an existing Automatic Speech Recognition (ASR) engine to convert the speech to text. Thereafter, macro features like accuracy, fluency and prosodic features were used to build a scoring model. In the process, we introduced SimIntonation, short for similarity between spoken intonation pattern and "ideal" i.e…
In Spoken language understanding (SLU), a natural solution is concatenating pre-trained speech models (e.g. HuBERT) and pretrained language models (PLM, e.g. T5). Most previous works use pretrained language models with subword-based tokenization. However, the granularity of input units affects the alignment of speech model outputs and language model inputs, and PLM with character-based tokenization is underexplored. In this work, we conduct extensive studies on how PLMs with different tokenization strategies affect spoken language understanding task including spoken question answering (SQA) an…
SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Guangdong Provincial Public Security Department（广东省公安厅）；Shanghai Jiao Tong University（上海交通大学）
In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU models have been proposed to directly map speech input to desired semantic frame with a single model, hence mitigating ASR error propagation. Recently, pre-training technologies have been explored for these E2E models. In this paper, we propose a novel joint textual-phonetic pre-training approach for learning spoken language representations, aiming at explo…
