Text-Speech Language Models with Improved Cross-Modal Transfer by Aligning Abstraction Levels

Text-Speech Language Models (TSLMs) -- language models trained to jointly process and generate text and speech -- aim to enable cross-modal knowledge transfer to overcome the scaling limitations of unimodal speech LMs. The predominant approach to TSLM training expands the vocabulary of a pre-trained text LM by appending new embeddings and linear projections for speech, followed by fine-tuning on speech data. We hypothesize that this method limits cross-modal transfer by neglecting feature compositionality, preventing text-learned functions from being fully leveraged at appropriate abstraction levels. To address this, we propose augmenting vocabulary expansion with modules that better align abstraction levels across layers. Our models, \textsc{SmolTolk}, rival or surpass state-of-the-art TSLMs trained with orders of magnitude more compute. Representation analyses and improved multimodal performance suggest our method enhances cross-modal transfer.

SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers

We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for controlling an autoregressive generative music transformer using classifier probes. These simple logistic regression probes are trained on the output of each attention head in the transformer using a small dataset of audio examples both exhibiting and missing a specific musical trait (e.g., the presence/absence of drums, or real/synthetic music). We then steer the attention heads in the probe direction, ensuring the generative model output captures the desired musical trait. Additionally, we monitor the probe output to avoid adding an excessive amount of intervention into the autoregressive generation, which could lead to temporally incoherent music. We validate our results objectively and subjectively for both audio continuation and text-to-music applications, demonstrating the ability to add controls to large generative models for which retraining or even fine-tuning is impractical for most musicians. Audio samples of the proposed intervention approach are available on our demo page http://tinyurl.com/smitin .

NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization

Head-related transfer functions (HRTFs) are important for immersive audio, and their spatial interpolation has been studied to upsample finite measurements. Recently, neural fields (NFs) which map from sound source direction to HRTF have gained attention. Existing NF-based methods focused on estimating the magnitude of the HRTF from a given sound source direction, and the magnitude is converted to a finite impulse response (FIR) filter. We propose the neural infinite impulse response filter field (NIIRF) method that instead estimates the coefficients of cascaded IIR filters. IIR filters mimic the modal nature of HRTFs, thus needing fewer coefficients to approximate them well compared to FIR filters. We find that our method can match the performance of existing NF-based methods on multiple datasets, even outperforming them when measurements are sparse. We also explore approaches to personalize the NF to a subject and experimentally find low-rank adaptation to be effective.

NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection

Neuro-steered speaker extraction aims to extract the listener's brain-attended speech signal from a multi-talker speech signal, in which the attention is derived from the cortical activity. This activity is usually recorded using electroencephalography (EEG) devices. Though promising, current methods often have a high speaker confusion error, where the interfering speaker is extracted instead of the attended speaker, degrading the listening experience. In this work, we aim to reduce the speaker confusion error in the neuro-steered speaker extraction model through a jointly fine-tuned auxiliary auditory attention detection model. The latter reinforces the consistency between the extracted target speech signal and the EEG representation, and also improves the EEG representation. Experimental results show that the proposed network significantly outperforms the baseline in terms of speaker confusion and overall signal quality in two-talker scenarios.

Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction

Target speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers. Building upon the achievements of the state-of-the-art (SOTA) time-frequency speaker separation model TF-GridNet, we propose AV-GridNet, a visual-grounded variant that incorporates the face recording of a target speaker as a conditioning factor during the extraction process. Recognizing the inherent dissimilarities between speech and noise signals as interfering sources, we also propose SAV-GridNet, a scenario-aware model that identifies the type of interfering scenario first and then applies a dedicated expert model trained specifically for that scenario. Our proposed model achieves SOTA results on the second COG-MHEAR Audio-Visual Speech Enhancement Challenge, outperforming other models by a significant margin, objectively and in a listening test. We also perform an extensive analysis of the results under the two scenarios.

Generation or Replication: Auscultating Audio Latent Diffusion Models

The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio. In this work, we make an initial attempt at understanding the inner workings of audio latent diffusion models by investigating how their audio outputs compare with the training data, similar to how a doctor auscultates a patient by listening to the sounds of their organs. Using text-to-audio latent diffusion models trained on the AudioCaps dataset, we systematically analyze memorization behavior as a function of training set size. We also evaluate different retrieval metrics for evidence of training data memorization, finding the similarity between mel spectrograms to be more robust in detecting matches than learned embedding vectors. In the process of analyzing memorization in audio latent diffusion models, we also discover a large amount of duplicated audio clips within the AudioCaps database.

Direct Text to Speech Translation System using Acoustic Units

This paper proposes a direct text to speech translation system using discrete acoustic units. This framework employs text in different source languages as input to generate speech in the target language without the need for text transcriptions in this language. Motivated by the success of acoustic units in previous works for direct speech to speech translation systems, we use the same pipeline to extract the acoustic units using a speech encoder combined with a clustering algorithm. Once units are obtained, an encoder-decoder architecture is trained to predict them. Then a vocoder generates speech from units. Our approach for direct text to speech translation was tested on the new CVSS corpus with two different text mBART models employed as initialisation. The systems presented report competitive performance for most of the language pairs evaluated. Besides, results show a remarkable improvement when initialising our proposed architecture with a model pre-trained with more languages.

Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translation via semantic knowledge distillation. We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, a multilingual speech transformer encoder trained using multi-modal (speech-text) semantic knowledge distillation, we achieve significantly better cross-lingual task knowledge transfer than the baseline XLS-R, a multilingual speech transformer encoder trained via self-supervised learning. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl. On the 21 translation tasks of the CoVoST-2 benchmark, we achieve an average improvement of 12.8 BLEU points over the baselines. In the zero-shot translation scenario, we achieve an average gain of 18.8 and 11.9 average BLEU points on unseen medium and low-resource languages. We make similar observations on Europarl speech translation benchmark.

Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages

Recent models such as XLS-R and Whisper have made multilingual speech technologies more accessible by pre-training on audio from around 100 spoken languages each. However, there are thousands of spoken languages worldwide, and adapting to new languages is an important problem. In this work, we aim to understand which model adapts better to languages unseen during pre-training. We fine-tune both models on 13 unseen languages and 18 seen languages. Our results show that the number of hours seen per language and language family during pre-training is predictive of how the models compare, despite the significant differences in the pre-training methods.