International audience

International audience

This paper introduces SENSE (Shared Embedding for Nlingual Speech and tExt), an open-source solution inspired by the SAMUXLSR framework and conceptually similar to Meta AI’s SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder. The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders.

Published in Interspeech 2025

International audience

In recent years, there has been a significant increase in interest in developing Spoken Language Understanding (SLU) systems. SLU involves extracting a list of semantic information from the speech signal. A major issue for SLU systems is the lack of sufficient amount of bi-modal (audio and textual semantic annotation) training data. Existing SLU resources are mainly available in high-resource languages such as English, Mandarin and French. However, one of the current challenges concerning low-resourced languages is data collection and annotation. In this work, we present a new freely available corpus, named TARIC-SLU, composed of railway transport conversations in Tunisian dialect that is continuously annotated in dialogue acts and slots. We describe the semantic model of the dataset, the data and experiments conducted to build ASR-based and SLU-based baseline models. To facilitate its use, a complete recipe, including data preparation, training and evaluation scripts, has been built and will be integrated to SpeechBrain, a popular open-source conversational AI toolkit based on PyTorch.

Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled demographic tags. This paper introduces the Sonos Voice Control Bias Assessment Dataset, an open dataset composed of voice assistant requests for North American English in the music domain (1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts) with a controlled demographic diversity (gender, age, dialectal region and ethnicity). We also release a statistical demographic bias assessment methodology, at the univariate and multivariate levels, tailored to this specific use case and leveraging spoken language understanding metrics rather than transcription accuracy, which we believe is a better proxy for user experience. To demonstrate the capabilities of this dataset and statistical method to detect demographic bias, we consider a pair of state-of-the-art Automatic Speech Recognition and Spoken Language Understanding models. Results show statistically significant differences in performance across age, dialectal region and ethnicity. Multivariate tests are crucial to shed light on mixed effects between dialectal region, gender and age.

International audience

SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete recipes of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.

This paper presents a study on the use of federated learning to train an ASR model based on a wav2vec 2.0 model pre-trained by self supervision. Carried out on the well-known TED-LIUM 3 dataset, our experiments show that such a model can obtain, with no use of a language model, a word error rate of 10.92% on the official TEDLIUM 3 test set, without sharing any data from the different users. We also analyse the ASR performance for speakers depending to their participation to the federated learning. Since federated learning was first introduced for privacy purposes, we also measure its ability to protect speaker identity. To do that, we exploit an approach to analyze information contained in exchanged models based on a neural network footprint on an indicator dataset. This analysis is made layer-wise and shows which layers in an exchanged wav2vec 2.0based model bring the speaker identity information.

The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR. In both cases, personalized acoustic models (AM), i.e. fine-tuned AM with specific speaker data, can be built. A question that naturally arises is whether the dissemination of personalized acoustic models can leak personal information. In this paper, we show that it is possible to retrieve the gender of the speaker, but also his identity, by just exploiting the weight matrix changes of a neural acoustic model locally adapted to this speaker. Incidentally we observe phenomena that may be useful towards explainability of deep neural networks in the context of speech processing. Gender can be identified almost surely using only the first layers and speaker verification performs well when using middle-up layers. Our experimental study on the TED-LIUM 3 dataset with HMM/TDNN models shows a purity of 95% for gender detection, and an Equal Error Rate of 9.07% for a speaker verification task by only exploiting the weights from personalized models that could be exchanged instead of user data.

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the context of federated learning of ASR acoustic models where a global model is learnt on the server based on the updates received from multiple clients. We propose an approach to analyze information in neural network AMs based on a neural network footprint on the so-called Indicator dataset. Using this method, we develop two attack models that aim to infer speaker identity from the updated personalized models without access to the actual users’ speech data. Experiments on the TED-LIUM 3 corpus demonstrate that the proposed approaches are very effective and can provide equal error rate (EER) of 1–2%.

Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU).Through the term end-to-end, one considers the use of a single model optimized to extract semantic information directly from the speech signal.A major issue for such models is the lack of paired audio and textual data with semantic annotation.In this paper, we propose an approach to build an end-to-end neural model to extract semantic information in a scenario in which zero paired audio data is available.Our approach is based on the use of an external model trained to generate a sequence of vectorial representations from text.These representations mimic the hidden representations that could be generated inside an end-to-end automatic speech recognition (ASR) model by processing a speech signal.A SLU neural module is then trained using these representations as input and the annotated text as output.Last, the SLU module replaces the top layers of the ASR model to achieve the construction of the end-to-end model.Our experiments on named entity recognition, carried out on the QUAERO corpus, show that this approach is very promising, getting better results than a comparable cascade approach or than the use of synthetic voices.

With the emergence of neural end-to-end approaches for spoken language understanding (SLU), a growing number of studies have been presented during these last three years on this topic. The major part of these works addresses the spoken language understanding domain through a simple task like speech intent detection. In this context, new benchmark datasets have also been produced and shared with the community related to this task. In this paper, we focus on the French MEDIA SLU dataset, distributed since 2005 and used as a benchmark dataset for a large number of research works. This dataset has been shown as being the most challenging one among those accessible to the research community. Distributed by ELRA, this corpus is free for academic research since 2019. Unfortunately, the MEDIA dataset is not really used beyond the French research community. To facilitate its use, a complete recipe, including data preparation, training and evaluation scripts, has been built and integrated to SpeechBrain, an already popular open-source and all-in-one conversational AI toolkit based on PyTorch. This recipe is presented in this paper. In addition, based on the feedback of some researchers who have worked on this dataset for several years, some corrections have been brought to the initial manual annotation: the new version of the data will also be integrated into the ELRA catalogue, as the original one. More, a significant amount of data collected during the construction of the MEDIA corpus in the 2000s was never used until now: we present the first results reached on this subset — also included in the MEDIA SpeechBrain recipe — , that will be used for now as the MEDIA test2. Last, we discuss evaluation issues.

Pretrained models through self-supervised learning have been recently introduced for both acoustic and language modeling. Applied to spoken language understanding tasks, these models have shown their great potential by improving the state-of-the-art performances on challenging benchmark datasets. In this paper, we present an error analysis reached by the use of such models on the French MEDIA benchmark dataset, known as being one of the most challenging benchmarks for the slot filling task among all the benchmarks accessible to the entire research community. One year ago, the state-of-art system reached a Concept Error Rate (CER) of 13.6% through the use of a end-to-end neural architecture. Some months later, a cascade approach based on the sequential use of a fine-tuned wav2vec2.0 model and a fine-tuned BERT model reaches a CER of 11.2%. This significant improvement raises questions about the type of errors that remain difficult to treat, but also about those that have been corrected using these models pre-trained through self-supervision learning on a large amount of data. This study brings some answers in order to better understand the limits of such models and open new perspectives to continue improving the performance.

Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. They were notably successful to improve performance on downstream tasks such as automatic speech recognition (ASR). While these works suggest it is possible to reduce dependence on labeled data for building efficient speech systems, their evaluation was mostly made on ASR and using multiple and heterogeneous experimental settings (most of them for English). This questions the objective comparison of SSL approaches and the evaluation of their impact on building speech systems. In this paper, we propose LeBenchmark: a reproducible framework for assessing SSL from speech. It not only includes ASR (high and low resource) tasks but also spoken language understanding, speech translation and emotion recognition. We also focus on speech technologies in a language different than English: French. SSL models of different sizes are trained from carefully sourced and documented datasets. Experiments show that SSL is beneficial for most but not all tasks which confirms the need for exhaustive and reliable benchmarks to evaluate its real impact. LeBenchmark is shared with the scientific community for reproducible research in SSL from speech.

This corpus is part of the PASTEL (Performing Automated Speech Transcription for Enhancing Learning) project aiming to explore the potential of synchronous speech transcription and application in specific teaching situations. It includes 10 hours of different lectures, manually transcribed and segmented. The main interest of this corpus lies in its multimodal aspect: in addition to speech, the courses were filmed and the written presentation supports (slides) are made available. The dataset may then serve researches in multiple fields, from speech and language to image and video processing. The dataset will be freely available to the research community. In this paper, we first describe in details the annotation protocol, including a detailed analysis of the manually labeled data. Then, we propose some possible use cases of the corpus with baseline results. The use cases concern scientific fields from both speech and text processing, with language model adaptation, thematic segmentation and transcription to slide alignment.

This paper presents the ongoing conception of a set of tools, based on live transcription of speech during lectures and designed to instrument traditional lectures as well as web conferences or hybrid learning situations. The toolset exploits speech and interactions taking place during courses, keeps track of them and facilitates their reuse both in students' studies and in future iterations of the course delivered by the teacher. Its goal is to help students stay focused on the teacher's explanations and offer them greater possibilities of interactions. The prototype was conceived with an approach based on the analysis of communicational and informational needs of the end users, especially in regard to the instrumentation possibilities offered by the innovative technologies considered in the project. In this paper, we detail the different tools produced in order to offer synchronous and asynchronous support to the learning activity. We describe a real-life test as well as changes brought to the device afterwards, and finally we describe the first experiment conducted with the device.

International audience

Modern Standard Arabic, as well as Arabic dialect languages, are usually written without diacritics. The absence of these marks constitute a real problem in the automatic processing of these data by NLP tools. Indeed, writing Arabic without diacritics introduces several types of ambiguity. First, a word without diacratics could have many possible meanings depending on their diacritization. Second, undiacritized surface forms of an Arabic word might have as many as 200 readings depending on the complexity of its morphology [12]. In fact, the agglutination property of Arabic might produce a problem that can only be resolved using diacritics. Third, without diacritics a word could have many possible parts of speech (POS) instead of one. This is the case with the words that have the same spelling and POS tag but a different lexical sense, or words that have the same spelling but different POS tags and lexical senses [8]. Finally, there is ambiguity at the grammatical level (syntactic ambiguity). In this article, we propose the first work that investigates the automatic diacritization of Tunisian Dialect texts. We first describe our annotation guidelines and procedure. Then, we propose two major models, namely a statistical machine translation (SMT) and a discriminative model as a sequence classification task based on Conditional Random Fields (CRF). In the second approach, we integrate POS features to influence the generation of diacritics. Diacritics restoration was performed at both the word and the character levels. The results showed high scores of automatic diacritization based on the CRF system (Word Error Rate (WER) 21.44% for CRF and WER 34.6% for SMT).