Enhancing expressivity transfer in textless speech-to-speech translation

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring expressivity accurately across different languages. Expressivity plays a vital role in conveying emotions, nuances, and cultural subtleties, thereby enhancing communication across diverse languages. To address this issue this study presents a novel method that operates at the discrete speech unit level and leverages multilingual emotion embeddings to capture language-agnostic information. Specifically, we demonstrate how these embeddings can be used to effectively predict the pitch and duration of speech units in the target language. Through objective and subjective experiments conducted on a French-to-English translation task, our findings highlight the superior expressivity transfer achieved by our approach compared to current state-of-the-art systems.

LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech

Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current domain-related tasks are now being approached with pre-trained models. This work introduces LeBenchmark 2.0 an open-source framework for assessing and building SSL-equipped French speech technologies. It includes documented, large-scale and heterogeneous corpora with up to 14,000 hours of heterogeneous speech, ten pre-trained SSL wav2vec 2.0 models containing from 26 million to one billion learnable parameters shared with the community, and an evaluation protocol made of six downstream tasks to complement existing benchmarks. LeBenchmark 2.0 also presents unique perspectives on pre-trained SSL models for speech with the investigation of frozen versus fine-tuned downstream models, task-agnostic versus task-specific pre-trained models as well as a discussion on the carbon footprint of large-scale model training.

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of comprehensive benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, while the number of considered tasks has been growing, most proposals rely upon a single downstream architecture that maps the frozen SSL representations to the task labels. This study examines how benchmarking results are affected by changes in the probing head architecture. Interestingly, we found that altering the downstream architecture structure leads to significant fluctuations in the performance ranking of the evaluated models. Against common practices in speech SSL benchmarking, we evaluate larger-capacity probing heads, showing their impact on performance, inference costs, generalization and multi-level feature exploitation.

Sumformer: A Linear-Complexity Alternative to Self-Attention for Speech Recognition

Modern speech recognition systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference as well as training and increasing memory consumption. Cheaper alternatives to self-attention for ASR have been developed, but fail to consistently reach the same level of accuracy. In practice, however, the self-attention weights of trained speech recognizers take the form of a global average over time. This paper, therefore, proposes a linear-time alternative to self-attention for speech recognition. It summarises a whole utterance with the mean over vectors for all time steps. This single summary is then combined with time-specific information. We call this method ``Summary Mixing''. Introducing Summary Mixing in state-of-the-art ASR models makes it feasible to preserve or exceed previous speech recognition performance while lowering the training and inference times by up to 27% and reducing the memory budget by a factor of two.

Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data

We propose a method for speech-to-speech emotionpreserving translation that operates at the level of discrete speech units. Our approach relies on the use of multilingual emotion embedding that can capture affective information in a language-independent manner. We show that this embedding can be used to predict the pitch and duration of speech units in a target language, allowing us to resynthesize the source speech signal with the same emotional content. We evaluate our approach to English and French speech signals and show that it outperforms a baseline method that does not use emotional information, including when the emotion embedding is extracted from a different language. Even if this preliminary study does not address directly the machine translation issue, our results demonstrate the effectiveness of our approach for cross-lingual emotion preservation in the context of speech resynthesis.

Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while facing an acoustic mismatch between the pretraining and target datasets. To address this issue, we propose a novel supervised domain adaptation method, designed for cases exhibiting such a mismatch in acoustic domains. It consists in applying properly calibrated data augmentations on a large clean dataset, bringing it closer to the target domain, and using it as part of an initial fine-tuning stage. Augmentations are automatically selected through the minimization of a conditional-dependence estimator, based on the target dataset. The approach is validated during an oracle experiment with controlled distortions and on two amateur-collected low-resource domains, reaching better performances compared to the baselines in both cases.

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts of annotated data. The high number of proposed approaches fostered the need and rise of extended benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, and while the number of considered tasks has been growing, most rely upon a single decoding architecture that maps the frozen SSL representations to the downstream labels. This work investigates the robustness of such benchmarking results to changes in the decoder architecture. Interestingly, it appears that varying the architecture of the downstream decoder leads to significant variations in the leaderboards of most tasks. Concerningly, our study reveals that benchmarking using limited decoders may cause a counterproductive increase in the sizes of the developed SSL models.

HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are expensive for long input sequences. Here, we address this by extending HyperMixer, an efficient alternative to attention exhibiting linear complexity, to the Conformer architecture for speech recognition, leading to HyperConformer. In particular, multi-head HyperConformer achieves comparable or higher recognition performance while being more efficient than Conformer in terms of inference speed, memory, parameter count, and available training data. HyperConformer achieves a word error rate of 2.9% on Librispeech test-clean with less than 8M neural parameters and a peak memory during training of 5.7GB, hence trainable with accessible hardware. Encoder speed is between 38% on mid-length speech and 56% on long speech faster than an equivalent Conformer. (The HyperConformer recipe is publicly available in: https://github.com/speechbrain/speechbrain/tree/develop/recipes/LibriSpeech/ASR/transformer/)

Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial for achieving lower downstream ASR error rates. Thus, better performance might be sanctioned with longer inferences. This article explores different approaches that may be deployed during the fine-tuning to reduce the computations needed in the SSL encoder, leading to faster inferences. We adapt a number of existing techniques to common ASR settings and benchmark them, displaying performance drops and gains in inference times. Interestingly, we found that given enough downstream data, a simple downsampling of the input sequences outperforms the other methods with both low performance drops and high computational savings, reducing computations by 61.3% with an WER increase of only 0.81. Finally, we analyze the robustness of the comparison to changes in dataset conditions, revealing sensitivity to dataset size.

Stabilising and accelerating light gated recurrent units for automatic speech recognition

The light gated recurrent units (Li-GRU) is well-known for achieving impressive results in automatic speech recognition (ASR) tasks while being lighter and faster to train than a standard gated recurrent units (GRU). However, the unbounded nature of its rectified linear unit on the candidate recurrent gate induces an important gradient exploding phenomenon disrupting the training process and preventing it from being applied to famous datasets. In this paper, we theoretically and empirically derive the necessary conditions for its stability as well as engineering mechanisms to speed up by a factor of five its training time, hence introducing a novel version of this architecture named SLi-GRU. Then, we evaluate its performance both on a toy task illustrating its newly acquired capabilities and a set of three different ASR datasets demonstrating lower word error rates compared to more complex recurrent neural networks.