Related papers: TorchAudio-Squim: Reference-less Speech Quality an…

Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability…

Standard training for Multi-modal Large Language Models (MLLMs) involves concatenating non-textual information, like vision or audio, with a text prompt. This approach may not encourage deep integration of modalities, limiting the model's…

Perceptual Evaluation of Speech Quality (PESQ) is an objective quality measure that remains widely used despite its withdrawal by the International Telecommunication Union (ITU). PESQ has evolved over two decades, with multiple versions and…

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…

Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. Although effective, these systems provide only numerical scores, without the information needed to help learners understand their…

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and…

The DIVA model is a computational model of speech motor control that combines a simulation of the brain regions responsible for speech production with a model of the human vocal tract. The model is currently implemented in Matlab Simulink;…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging. Benchmarks derived from published studies and human annotations inherit publication bias,…

In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based…

Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To…

The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical…

Personalized speech intelligibility prediction is challenging. Previous approaches have mainly relied on audiograms, which are inherently limited in accuracy as they only capture a listener's hearing threshold for pure tones. Rather than…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes…

While the automatic evaluation of omni-modal large models (OLMs) is essential, assessing empathy remains a significant challenge due to its inherent affectivity. To investigate this challenge, we introduce AEQ-Bench (Audio Empathy Quotient…

We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional…

Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their…

Spoken Question-Answering (SQA) is a core capability for useful and interactive artificial intelligence systems. Recently, several speech-language models (SpeechLMs) have been released with a specific focus on improving their SQA…

Automatic speech intelligibility assessment is crucial for monitoring speech disorders and therapy efficacy. However, existing methods are difficult to compare: research is fragmented across private datasets with inconsistent protocols. We…