本文介绍了我们构建流式多语言语音模型（SM2）的工作，该模型可以将多种口语语音转录或翻译成目标语言的文本。SM2 的主干网络是 Transformer Transducer，具有很高的流式处理能力。SM2 模型不使用人工标注的语音翻译（ST）数据，而是使用弱监督数据进行训练，这些数据通过机器翻译服务转换语音识别语料库中的转录文本而生成。利用来自 25 种语言的 351 千小时匿名语音训练数据，SM2 模型取得了与近期一些流行的大规模非流式语音模型相当甚至更好的 ST 质量。更重要的是，我们表明 SM2 在扩展到新的目标语言时具有真正的零样本能力，能够为训练期间未见过的{源语音，目标文本}对生成高质量的 ST 结果。
英文摘要：
In this paper, we introduce our work of building a Streaming Multilingual Speech Model (SM2), which can transcribe or translate multiple spoken languages into texts of the target language. The backbone of SM2 is Transformer Transducer, which has high streaming capability. Instead of human labeled speech translation (ST) data, SM2 models are trained using weakly supervised data generated by converting the transcriptions in speech recognition corpora with a machine translation service. With 351 thousand hours of anonymized speech training data from 25 languages, SM2 models achieve comparable or even better ST quality than some recent popular large-scale non-streaming speech models. More importantly, we show that SM2 has the truly zero-shot capability when expanding to new target languages, yielding high quality ST results for {source-speech, target-text} pairs that are not seen during training.
On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising results for multilingual automatic speech recognition (ASR). In this paper, we extend our previous capacity solution to streaming applications and present a streaming multilingual E2E ASR system that runs fully on device with comparable quality and latency to individual monolingual models. To achieve that, we propose an Encoder Endpointer model and an End-of-Utterance (EOU) Joint Layer for a better quality and latenc…
Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. B…
This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language. Conventionally, LID relies on acoustic only information to detect input language. We propose an approach that learns and combines acoustic level representations with embeddings estimated on ASR hypothese…
Word-piece models (WPMs) are commonly used subword units in state-of-the-art end-to-end automatic speech recognition (ASR) systems. For multilingual ASR, due to the differences in written scripts across languages, multilingual WPMs bring the challenges of having overly large output layers and scaling to more languages. In this work, we propose a universal monolingual output layer (UML) to address such problems. Instead of one output node for only one WPM, UML re-associates each output node with multiple WPMs, one for each language, and results in a smaller monolingual output layer shared acros…
Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on understanding the languages behaviour in the multilingual speech recognition setups. In this paper, a novel data-driven approach is proposed to investigate the cross-lingual acoustic-phonetic similarities. This technique measures the similarities between posterior distributions from various monolingual acoustic models against a target speech signal. Deep neural net…
Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming End-to-End ASR models. However, the pivotal characteristics of SSL is to be utilized for any untranscribed audio data. In this paper, we provide a full exploration on how to utilize uncurated audio data in SSL from data pre-processing to deploying an streaming hybrid ASR model. More specifically, we present (1) the effect of Audio Event Detection (AED) model in da…
Neural transducers have been widely used in automatic speech recognition (ASR). In this paper, we introduce it to streaming end-to-end speech translation (ST), which aims to convert audio signals to texts in other languages directly. Compared with cascaded ST that performs ASR followed by text-based machine translation (MT), the proposed Transformer transducer (TT)-based ST model drastically reduces inference latency, exploits speech information, and avoids error propagation from ASR to MT. To improve the modeling capacity, we propose attention pooling for the joint network in TT. In addition,…
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer…
Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language identity is seldom known beforehand in real-world scenarios, it must be inferred on-the-fly with minimum latency. Furthermore, in voice-activated smart assistant systems, language identity is also required for downstream processing of ASR output. In this paper, we introduce streaming, end-to-end, bilingual systems that perform both ASR and language identification (LID) using the recurrent neural network transducer (RNN-…
We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook is updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the a…
YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech
Carnegie Mellon University（卡内基梅隆大学）；Keio University（庆应义塾大学）；Tokyo Metropolitan University（东京都立大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所）
Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a novel multilingual task adaptation approach based on contextual parameter generation and adapter modules. This approach enables to learn adapters via language embeddings while sharing model parameters across languages. It also allows for an easy but effective integration of existing linguistic typology features into the parsing network. The resulting parser…
University of Edinburgh（爱丁堡大学）；Priberam Labs（Priberam实验室）；Innovation Labs LETA（LETA创新实验室）；University of Latvia（拉脱维亚大学）
Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories. Doing so in an online setting allows scalable processing of massive news streams. To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters. Unlike typical clustering approaches that consider a small and known number of labels, we tackle the problem of discovering an ever growing number of cluster labels in an online fashion, using real news datasets in multiple lan…
The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses a fully connected layer as the joint network to fuse the acoustic representations extracted using the acoustic encoder with the text representations obtained using the prediction network based on the previous subword units. In this paper, we propose to use gating, bilinear pooling, and a combination of them in the joint network to produce more expressive representations to fee…
Nowadays, digital news articles are widely available, published by various editors and often written in different languages. This large volume of diverse and unorganized information makes human reading very difficult or almost impossible. This leads to a need for algorithms able to arrange high amount of multilingual news into stories. To this purpose, we extend previous works on Topic Detection and Tracking, and propose a new system inspired from newsLens. We process articles per batch, looking for monolingual local topics which are then linked across time and languages. Here, we introduce a …
University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Stuttgart（斯图加特大学）；University of Edinburgh（爱丁堡大学）；Microsoft Turing（微软图灵）；Facebook AI Research（脸书人工智能研究院）；New York University（纽约大学）；Universidad de la República, Uruguay（乌拉圭共和国大学）；Universidad Tecnológica de Tlaxcala（特拉斯卡拉理工大学）；University of Zurich（苏黎世大学）；Carnegie Mellon University（卡内基梅隆大学）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）；Universidade Tecnológica Federal do Paraná（巴拉那联邦理工大学）；Dartmouth College（达特茅斯学院）
Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating performance on unseen languages has largely been limited to low-level, syntactic tasks, and it remains unclear if zero-shot learning of high-level, semantic tasks is possible for unseen languages. To explore this question, we present AmericasNLI, an extension of XNLI (Conneau et al., 2018) to 10 indigenous languages of the Americas. We conduct experiments with XLM-R, testing multiple zero-shot and translation-based approa…
Amazon Alexa AI（亚马逊Alexa AI）；University of Groningen（格罗宁根大学）
We investigate whether off-the-shelf deep bidirectional sentence representations trained on a massively multilingual corpus (multilingual BERT) enable the development of an unsupervised universal dependency parser. This approach only leverages a mix of monolingual corpora in many languages and does not require any translation data making it applicable to low-resource languages. In our experiments we outperform the best CoNLL 2018 language-specific systems in all of the shared task's six truly low-resource languages while using a single system. However, we also find that (i) parsing accuracy st…
Multilingual models are parameter-efficient and especially effective in improving low-resource languages by leveraging crosslingual transfer. Despite recent advance in massive multilingual translation with ever-growing model and data, how to effectively train multilingual models has not been well understood. In this paper, we show that a common situation in multilingual training, data imbalance among languages, poses optimization tension between high resource and low resource languages where the found multilingual solution is often sub-optimal for low resources. We show that common training me…
This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between the source and target language. More precisely, our method has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about foreign languages, which makes it applicable to a wide range of resource-po…
Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
University of Notre Dame（诺特达姆大学）；University of Washington（华盛顿大学）；Tokyo University of Foreign Studies（东京外国语大学）；Nara Institute of Science and Technology（奈良科学技術大学）；University of Tübingen（图宾根大学）
University of Cambridge（剑桥大学）；University of Würzburg（维尔茨堡大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；PolyAI Limited（PolyAI有限公司）
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task. Although this technology represents one of the central objectives of AI and has been the focus of ever more intense research and development efforts, it is currently limited to a few narrow domains (e.g., food ordering, ticket booking) and a handful of languages (e.g., English, Chinese). This work provides an extensive overview of existing methods and resources in multilingual ToD as an entry point to this exciting and emerging field. We find that the most critical factor preventi…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language with a large treebank to a language with a small or nonexistent treebank, by sharing parameters between languages in the parser itself. We experiment with a diverse selection of languages in both simulated and truly low-resource scenarios, and show that multilingual CWRs greatly facilitate low-resource dependency parsing even without crosslingual supervision…
We introduce a few-shot transfer learning method for keyword spotting in any language. Leveraging open speech corpora in nine languages, we automate the extraction of a large multilingual keyword bank and use it to train an embedding model. With just five training examples, we fine-tune the embedding model for keyword spotting and achieve an average F1 score of 0.75 on keyword classification for 180 new keywords unseen by the embedding model in these nine languages. This embedding model also generalizes to new languages. We achieve an average F1 score of 0.65 on 5-shot models for 260 keywords …
