我们提出了一种新颖的语言通用端到端自动口语关键词识别（SKR）方法，利用（i）自监督预训练模型和（ii）一组通用语音属性（发音方式和发音部位）。具体而言，Wav2Vec2.0用于生成鲁棒的语音表示，随后通过线性输出层产生属性序列。然后，一个不可训练的发音模型在多语言环境下将属性序列映射为口语关键词。在Multilingual Spoken Words Corpus上的实验表明，在已见语言中，其性能与基于字符和音素的SKR相当。引入领域对抗训练（DAT）改进了该框架，在已见语言中相对词错误率（WER）分别降低了13.73%和17.22%，优于基于字符和音素的SKR方法，并在零样本设置下对未见语言的WER降低了32.14%和19.92%。
英文摘要：
We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of articulation). Specifically, Wav2Vec2.0 is used to generate robust speech representations, followed by a linear output layer to produce attribute sequences. A non-trainable pronunciation model then maps sequences of attributes into spoken keywords in a multilingual setting. Experiments on the Multilingual Spoken Words Corpus show comparable performances to character- and phoneme-based SKR in seen languages. The inclusion of domain adversarial training (DAT) improves the proposed framework, outperforming both character- and phoneme-based SKR approaches with 13.73% and 17.22% relative word error rate (WER) reduction in seen languages, and achieves 32.14% and 19.92% WER reduction for unseen languages in zero-shot settings.
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Nanyang Technological University（南洋理工大学）
Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. To tackle such challenges, we propose a progressive continual learning strategy for small-footprint spoken keyword spotting (PCL-KWS). Specifically, the proposed PCL-KWS framework introduces a network instantiator to generate the task-specific sub-networks for remembering previously learned keywords. As a result, the PCL-KWS approach incrementally learns new keywords without forgetting prior knowledge. Besides, the keyword-aware network scaling mechanism of PCL-KWS constrains the growth …
Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. This problem will be more challenging if KWS models are further required for edge devices due to their limited memory. To alleviate such an issue, we propose a novel diversity-aware incremental learning method named Rainbow Keywords (RK). Specifically, the proposed RK approach introduces a diversity-aware sampler to select a diverse set from historical and incoming keywords by calculating classification uncertainty. As a result, the RK approach can incrementally learn new tasks without f…
State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching. Here, we present a study on QbE-STD performance using several monolingual as well as multilingual bottleneck features extracted from feed forward networks. Then, we propose to employ residual networks (ResNet) to estimate the bottleneck features and show significant improvements over the corresponding feed forward network based features. The neural networks are trained on G…
Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often perform sub-optimally for profane words as they are underrepresented in training corpora and not spoken clearly or completely. Exploration of this problem entirely in the audio domain has largely been limited by the lack of audio datasets. Building on these challenges, we propose ADIMA, a novel, linguistically diverse, ethically sourced, expert annotated and well-balanced multilingu…
Keyword Mamba: Spoken Keyword Spotting with State Space Models
School of Computer Science and Communication Engineering, Jiangsu University（江苏大学计算机科学与通信工程学院）；Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications（江苏大数据普适感知与智能农业应用工程研究中心）；Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture（省级计算智能与低空数字农业新技术重点实验室）
Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago. This has allowed the rapid embedding of deep KWS in a myriad of small electronic devices with different purposes like the activation of voice assistants. Prospects suggest a sustained growth in terms of social use of this technology. Thus, it is not surprising that deep KWS has become a hot research topic among speech scientists, who constantly look for KWS performance improvement and computat…
This paper focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State-of-the-art approaches primarily rely on dynamic time warping (DTW) based template matching techniques using phone posterior or bottleneck features extracted from a deep neural network (DNN). We use both monolingual and multilingual bottleneck features, and show that multilingual features perform increasingly better with more training languages. Previously, it has been shown that the DTW based matching can be replaced with a CNN based matching while using posterior features. He…
Columbia University（哥伦比亚大学）；Recognition Technologies, Inc.（识别技术公司）
Closed-set spoken language identification is the task of recognizing the language being spoken in a recorded audio clip from a set of known languages. In this study, a language identification system was built and trained to distinguish between Arabic, Spanish, French, and Turkish based on nothing more than recorded speech. A pre-existing multilingual dataset was used to train a series of acoustic models based on the Tedlium TDNN model to perform automatic speech recognition. The system was provided with a custom multilingual language model and a specialized pronunciation lexicon with language …
The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of practical significance in many applications of speech analytics, including those concerning low-resource languages, and large amount of multilingual and multi-genre data. We propose a two-stage approach, which comprises unsupervised acoustic modeling and decoding, followed by pattern mining in acoustic unit sequences. The whole process starts by deriving and mo…
Stellenbosch University（斯泰伦博斯大学）；UN Global Pulse（联合国全球脉动）；Makerere University（马凯雷雷大学）；University of Edinburgh（爱丁堡大学）
We compare features for dynamic time warping (DTW) when used to bootstrap keyword spotting (KWS) in an almost zero-resource setting. Such quickly-deployable systems aim to support United Nations (UN) humanitarian relief efforts in parts of Africa with severely under-resourced languages. Our objective is to identify acoustic features that provide acceptable KWS performance in such environments. As supervised resource, we restrict ourselves to a small, easily acquired and independently compiled set of isolated keywords. For feature extraction, a multilingual bottleneck feature (BNF) extractor, t…
Valencian Research Institute for Artificial Intelligence (VRAIN)（巴伦西亚人工智能研究所（VRAIN））
Current research into spoken language translation (SLT),or speech-to-text translation, is often hampered by the lack of specific data resources for this task, as currently available SLT datasets are restricted to a limited set of language pairs. In this paper we present Europarl-ST, a novel multilingual SLT corpus containing paired audio-text samples for SLT from and into 6 European languages, for a total of 30 different translation directions. This corpus has been compiled using the debates held in the European Parliament in the period between 2008 and 2012. This paper describes the corpus cr…
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabulary speech recognition for African languages: multilingual modeling and self-supervised learning. We gathered available open source data and collected data for 15 languages, and trained experimental models using these techniques. Our results show that pooling the small amounts of data available in multilingual end-to-end models, and pr…
In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic transcriptions or conventional speech recognition technology. While prior work has investigated this setting in the monolingual case using English speech data, this work represents the first effort to apply these techniques to languages beyond English. Using spoken captions collected in English and Hindi, we show that the same model architecture can be successful…
Advancing Topic Segmentation of Broadcasted Speech with Multilingual Semantic Embeddings
Fraunhofer Institute for Digital Media Technology（弗劳恩霍夫数字媒体技术研究所）；Fraunhofer Institute for Intelligent Analysis and Information Systems（弗劳恩霍夫智能分析与信息系统研究所）
Swiggy (Bundl Technologies India Limited)（Swiggy（印度邦德尔科技有限公司））
Spoken language Identification (LID) systems are needed to identify the language(s) present in a given audio sample, and typically could be the first step in many speech processing related tasks such as automatic speech recognition (ASR). Automatic identification of the languages present in a speech signal is not only scientifically interesting, but also of practical importance in a multilingual country such as India. In many of the Indian cities, when people interact with each other, as many as three languages may get mixed. These may include the official language of that province, Hindi and …
Imagine being able to show a system a visual depiction of a keyword and finding spoken utterances that contain this keyword from a zero-resource speech corpus. We formalise this task and call it visually prompted keyword localisation (VPKL): given an image of a keyword, detect and predict where in an utterance the keyword occurs. To do VPKL, we propose a speech-vision model with a novel localising attention mechanism which we train with a new keyword sampling scheme. We show that these innovations give improvements in VPKL over an existing speech-vision model. We also compare to a visual bag-o…
In spoken Keyword Search, the query may contain out-of-vocabulary (OOV) words not observed when training the speech recognition system. Using subword language models (LMs) in the first-pass recognition makes it possible to recognize the OOV words, but even the subword n-gram LMs suffer from data sparsity. Recurrent Neural Network (RNN) LMs alleviate the sparsity problems but are not suitable for first-pass recognition as such. One way to solve this is to approximate the RNNLMs by back-off n-gram models. In this paper, we propose to interpolate the conventional n-gram models and the RNNLM appro…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Hyundai Motor Company（现代汽车公司）；dot Inc.（42dot公司）
The goal of this work is to detect new spoken terms defined by users. While most previous works address Keyword Spotting (KWS) as a closed-set classification problem, this limits their transferability to unseen terms. The ability to define custom keywords has advantages in terms of user experience. In this paper, we propose a metric learning-based training strategy for user-defined keyword spotting. In particular, we make the following contributions: (1) we construct a large-scale keyword dataset with an existing speech corpus and propose a filtering method to remove data that degrade model tr…
This memo describes NTR/TSU winning submission for Low Resource ASR challenge at Dialog2021 conference, language identification track. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. Traditionally, the ASR task requires large volumes of labeled data that are unattainable for most of the world's languages, including most of the languages of Russia. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results in low-resource setting for the language identificat…
Carnegie Mellon University（卡内基梅隆大学）；SIL International（SIL国际）；National Research Council Canada（加拿大国家研究委员会）；ByteDance AI Lab（字节跳动人工智能实验室）
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a particular language) and their corresponding phones (the sounds that are actually spoken, which are language independent). This can lead to performance degradation when combining a variety of training languages, as identically annotated phonemes can actually correspond to several different underlying phonetic realizations. In t…
AdaKWS: Towards Robust Keyword Spotting with Test-Time Adaptation
The University of Melbourne（墨尔本大学）；Fortemedia Singapore（新加坡Fortemedia公司）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation process is obtaining a sufficient amount of training data. In this paper, we explore the effectiveness of synthesized speech data in training small, spoken term detection models of around 400k parameters. Instead of training such models directly on the audio or low level features such as MFCCs, we use a pre-trained speech embedding model trained to extract u…
University of Toronto（多伦多大学）；University Health Network（大学健康网络）；Hanoi University of Science and Technology（河内科技大学）；RWTH Aachen University（亚琛工业大学）；AppTek GmbH（AppTek公司）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；University of Cincinnati（辛辛那提大学）；College of William and Mary（威廉玛丽学院）
Qatar Computing Research Institute（卡塔尔计算研究所）；KanarI AI
With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In this study, we design a large multilingual end-to-end ASR using self-attention based conformer architecture. We trained the system using Arabic (Ar), English (En) and French (Fr) languages. We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptia…
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource constraints, especially in scenarios that require supporting multiple languages. We propose a new approach to enable multilingual speech recognition on edge devices. This approach uses both language identification and accent identification to select one of multiple monolingual ASR models on-the-fly, each fine-tuned for a particular accent. Initial results for both recognition performance and resource usage are promising with our approach using less than 1/12th of the memory consumed by other solutions.
Avaya（Avaya公司）；Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）；Poznan University of Technology（波兹南理工大学）；AGH University of Science and Technology（AGH科技大学）
Avaya Conversational Intelligence(ACI) is an end-to-end, cloud-based solution for real-time Spoken Language Understanding for call centers. It combines large vocabulary, real-time speech recognition, transcript refinement, and entity and intent recognition in order to convert live audio into a rich, actionable stream of structured events. These events can be further leveraged with a business rules engine, thus serving as a foundation for real-time supervision and assistance applications. After the ingestion, calls are enriched with unsupervised keyword extraction, abstractive summarization, an…
Automatic Speech Recognition (ASR) is the interdisciplinary subfield of computational linguistics that develops methodologies and technologies that enables the recognition and translation of spoken language into text by computers. It incorporates knowledge and research in linguistics, computer science, and electrical engineering fields. Sentiment analysis is contextual mining of text which identifies and extracts subjective information in the source material and helping a business to understand the social sentiment of their brand, product or service while monitoring online conversations. Accor…
In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode language discriminatory information in lower layers. Further, we demonstrate that the embeddings obtained from these layers are significantly robust to classify unseen languages and different acoustic environments without additional training. After fine-tuning a pre-trained Conformer model on the VoxLingua107 dataset, we achieve results similar to current state…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
The aim of this paper is to develop a flexible framework capable of automatically recognizing phonetic units present in a speech utterance of any language spoken in any mode. In this study, we considered two modes of speech: conversation, and read modes in four Indian languages, namely, Telugu, Kannada, Odia, and Bengali. The proposed approach consists of two stages: (1) Automatic speech mode classification (SMC) and (2) Automatic phonetic recognition using mode-specific multilingual phone recognition system (MPRS). In this work, the vocal tract and excitation source features are considered fo…
Indraprastha Institute of Information Technology Delhi（德里英德拉普拉斯塔信息技术学院）
Due to a drastic improvement in the quality of internet services worldwide, there is an explosion of multilingual content generation and consumption. This is especially prevalent in countries with large multilingual audience, who are increasingly consuming media outside their linguistic familiarity/preference. Hence, there is an increasing need for real-time and fine-grained content analysis services, including language identification, content transcription, and analysis. Accurate and fine-grained spoken language detection is an essential first step for all the subsequent content analysis algo…
This paper investigates different pretraining approaches to spoken language identification. The paper is based on our submission to the Oriental Language Recognition 2021 Challenge. We participated in two tracks of the challenge: constrained and unconstrained language recognition. For the constrained track, we first trained a Conformer-based encoder-decoder model for multilingual automatic speech recognition (ASR), using the provided training data that had transcripts available. The shared encoder of the multilingual ASR model was then finetuned for the language identification task. For the un…
A text-independent speaker recognition system relies on successfully encoding speech factors such as vocal pitch, intensity, and timbre to achieve good performance. A majority of such systems are trained and evaluated using spoken voice or everyday conversational voice data. Spoken voice, however, exhibits a limited range of possible speaker dynamics, thus constraining the utility of the derived speaker recognition models. Singing voice, on the other hand, covers a broader range of vocal and ambient factors and can, therefore, be used to evaluate the robustness of a speaker recognition system.…
