Speech large language models (speech-LLMs) integrate speech and text-based foundation models to provide a unified framework for handling a wide range of downstream tasks. In this paper, we introduce WHISMA, a speech-LLM tailored for spoken language understanding (SLU) that demonstrates robust performance in various zero-shot settings. WHISMA combines the speech encoder from Whisper with the Llama-3 LLM, and is fine-tuned in a parameter-efficient manner on a comprehensive collection of SLU-related datasets. Our experiments show that WHISMA significantly improves the zero-shot slot filling performance on the SLURP benchmark, achieving a relative gain of 26.6% compared to the current state-of-the-art model. Furthermore, to evaluate WHISMA's generalisation capabilities to unseen domains, we develop a new task-agnostic benchmark named SLU-GLUE. The evaluation results indicate that WHISMA outperforms an existing speech-LLM (Qwen-Audio) with a relative gain of 33.0%.
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…
Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these end-to-end models without a large amount of training data is difficult. We propose a method to reduce the data requirements of end-to-end SLU in which the model is first pre-trained to predict words and phonemes, thus learning good features for SLU. We introduce a new SLU dataset, Fluent Speech Commands, and show that our method improves performance both when the fu…
The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data with suitable labels are usually available. In this paper, we propose a novel text representation and training methodology that allows E2E SLU systems to be effectively constructed using these text resources. With very limited amounts of additional speech, we show that these models can be further improved to perform at levels close to similar systems built on t…
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…
Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for S…
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…
New York University（纽约大学）；IBM Research AI（IBM研究院人工智能实验室）
A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach presents some challenges. First, since speech can be considered as personally identifiable information, in some cases only automatic speech recognition (ASR) transcripts are accessible. Second, intent-labeled speech data is scarce. To address the first challenge, we propose a novel system that can predict intents from flexible types of inputs: speech, ASR transcri…
In spoken question answering, the 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 the systems to model complex dialogue flows given the speech documents. In this task, our main objective is to build the system to deal with conversational questions based on the audio recordings, and to explore the plausibility of providing more cues from dif…
In this paper we demonstrate spoken speech enhancement using electroencephalography (EEG) signals using a generative adversarial network (GAN) based model, gated recurrent unit (GRU) regression based model, temporal convolutional network (TCN) regression model and finally using a mixed TCN GRU regression model. We compare our EEG based speech enhancement results with traditional log minimum mean-square error (MMSE) speech enhancement algorithm and our proposed methods demonstrate significant improvement in speech enhancement quality compared to the traditional method. Our overall results demon…
The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech. Through work on the speech features, we focus on improving the model generalization ability with limited dysarthric data. Factorized Hierarchical Variational Auto-Encoders (FHVAE) trained unsupervisedly have shown their advantage in disentangling content and speaker representations. Earlier work showed that the dysarthria shows in both feature vectors. Here, we add adversarial training to bridge …
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）
A Virtual Patient (VP) is a powerful tool for training medical students to take patient histories, where responding to a diverse set of spoken questions is essential to simulate natural conversations with a student. The performance of such a Spoken Language Understanding system (SLU) can be adversely affected by both the presence of Automatic Speech Recognition (ASR) errors in the test data and a high degree of class imbalance in the SLU training data. While these two issues have been addressed separately in prior work, we develop a novel two-step training methodology that tackles both these i…
Institute of Computational Mathematics and Information Technologies（计算数学与信息技术研究所）；Kazan Federal University（喀山联邦大学）
We present RUSLAN -- a new open Russian spoken language corpus for the text-to-speech task. RUSLAN contains 22200 audio samples with text annotations -- more than 31 hours of high-quality speech of one person -- being the largest annotated Russian corpus in terms of speech duration for a single speaker. We trained an end-to-end neural network for the text-to-speech task on our corpus and evaluated the quality of the synthesized speech using Mean Opinion Score test. Synthesized speech achieves 4.05 score for naturalness and 3.78 score for intelligibility on a 5-point MOS scale.
While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning from the very successful BERT model for various text processing tasks, here we proposed an audio-and-text jointly learned SpeechBERT model. This model outperformed the conventional approach of cascading ASR with the following text question answering (TQA) model on datasets including ASR errors in answer spans, because the end-to-end model was shown to be ab…
Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an unsupervised manner. In the second stage, partial sequence matching and clustering are performed on the decoded subword sequences, resulting in a set of discovered words or phrases. A limitation of this approach is that the results of subword decoding could be erroneous, and the errors would impact the subsequent steps. While Siamese/Triplet network is one approach to learn segm…
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.
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
MediaTek Research（联发科技研究）；Graduate Institute of Communication Engineering, National Taiwan University（国立台湾大学通信工程研究所）；Artificial Intelligence Center of Research Excellence, National Taiwan University（国立台湾大学卓越人工智能研究中心）
End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance recordings and corresponding semantics may not always be available or sufficient to train an E2E SLU model in a real production environment. In this paper, we propose to unify a well-optimized E2E ASR encoder (speech) and a pre-trained language model encoder (language) into a transformer decoder. The unified speech-language pre-trained model (SLP) is continually e…
In a modern spoken language understanding (SLU) system, the natural language understanding (NLU) module takes interpretations of a speech from the automatic speech recognition (ASR) module as the input. The NLU module usually uses the first best interpretation of a given speech in downstream tasks such as domain and intent classification. However, the ASR module might misrecognize some speeches and the first best interpretation could be erroneous and noisy. Solely relying on the first best interpretation could make the performance of downstream tasks non-optimal. To address this issue, we intr…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of British Columbia（不列颠哥伦比亚大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）；Newcastle University（纽卡斯尔大学）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech signals into hidden units generated from acoustic unit discovery, we propose WavEmbed, a multimodal sequential autoencoder that predicts hidden units from a dense representation of speech. Secondly, we also propose S-HuBERT to induce meaning through knowledge distillation, in which a sentence embeddi…
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained speech recognizer and natural language understanding module. The downside of end-to-end SLU is that in-domain speech data must be recorded to train the model. In this paper, we propose a strategy for overcoming this requirement in which speech synthesis is used to generate a large synthetic training dataset from several artificial speakers. Experiments on two …
Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall system suffers from error propagation. In this paper, we propose a novel training method that enables pretrained contextual embeddings to process acoustic features. In particular, we extend it with an encoder of pretrained speech recognition systems in order to construct end-to-end spoken language understanding systems. Our proposed method is based on the t…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）；Bandung Institute of Technology（万隆理工学院）
Research about brain activities involving spoken word production is considerably underdeveloped because of the undiscovered characteristics of speech artifacts, which contaminate electroencephalogram (EEG) signals and prevent the inspection of the underlying cognitive processes. To fuel further EEG research with speech production, a method using three-mode tensor decomposition (time x space x frequency) is proposed to perform speech artifact removal. Tensor decomposition enables simultaneous inspection of multiple modes, which suits the multi-way nature of EEG data. In a picture-naming task, w…
End-to-end (E2E) spoken language understanding (SLU) systems avoid an intermediate textual representation by mapping speech directly into intents with slot values. This approach requires considerable domain-specific training data. In low-resource scenarios this is a major concern, e.g., in the present study dealing with SLU for dysarthric speech. Pretraining part of the SLU model for automatic speech recognition targets helps but no research has shown to which extent SLU on dysarthric speech benefits from knowledge transferred from other dysarthric speech tasks. This paper investigates the eff…
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）
From Read Speech to Spoken Digits: A Task-Specific Evaluation of Speech Privacy With Informed Attackers
Jade University of Applied Sciences（亚德应用科学大学）；Carl von Ossietzky Universität Oldenburg（奥尔登堡卡尔·冯·奥西茨基大学）；Fraunhofer Institute for Integrated Circuits (IIS)（弗劳恩霍夫集成电路研究所）
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
Seoul National University（首尔大学）；NAVER Cloud（NAVER云）；Artificial Intelligence Institute, Seoul National University（首尔大学人工智能研究院）；NAVER AI Lab（NAVER人工智能实验室）
Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this work, we explored partial fine-tuning and entire fine-tuning on wav2vec 2.0 and HuBERT pre-trained models for three non-ASR speech tasks: Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding. With simple proposed downstream frameworks, the best scores reached 79.58% weighted accuracy on speaker-dependent setting and 73.01% weigh…
