相关论文: Codec-SUPERB @ SLT 2024: A lightweight benchmark f…

Text-guided sound separation enables flexible audio editing, assistive listening, and open-domain source extraction, but systems such as AudioSep remain too expensive for low-latency edge or codec-mediated deployment. Existing neural audio…

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme…

Objective speech-quality metrics are widely used to assess codec performance. However, for neural codecs, it is often unclear which metrics provide reliable quality estimates. To address this, we evaluated 45 objective metrics by…

We propose a Perceiver-based sequence classifier to detect abnormalities in speech reflective of several neurological disorders. We combine this classifier with a Universal Speech Model (USM) that is trained (unsupervised) on 12 million…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Large Audio Language Models (LALMs) excel at semantic and paralinguistic tasks, yet their ability to perceive the fundamental physical attributes of audio such as pitch, loudness, and spatial location remains under-explored. To bridge this…

The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It…

Speech enhancement is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved speech enhancement performance, but they often come with a…

Scaling spoken language modeling requires speech tokens that are both efficient and universal. Recent work has proposed syllables as promising speech tokens at low temporal resolution, but existing models are constrained to English and fail…

We introduce the Massive Audio Embedding Benchmark (MAEB), a large-scale benchmark covering 30 tasks across speech, music, environmental sounds, and cross-modal audio-text reasoning in 100+ languages. We evaluate 50+ models and find that no…

We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of…

Code-switching poses a number of challenges and opportunities for multilingual automatic speech recognition. In this paper, we focus on the question of robust and fair evaluation metrics. To that end, we develop a reference benchmark data…

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

Neural audio codecs (NACs) have made significant advancements in recent years and are rapidly being adopted in many audio processing pipelines. However, they can introduce audio distortions which degrade speaker verification (SV)…

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

This paper describes the language identification and multilingual speech recognition system developed at Tallinn University of Technology for the Interspeech 2025 ML-SUPERB 2.0 Challenge. A hybrid language identification system is used,…

We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics from two previous benchmarks (2017 and 2019) and features two…

Neural audio coding has emerged as a vivid research direction by promising good audio quality at very low bitrates unachievable by classical coding techniques. Here, end-to-end trainable autoencoder-like models represent the state of the…

Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have…

Self-supervised language models are very effective at predicting high-level cortical responses during language comprehension. However, the best current models of lower-level auditory processing in the human brain rely on either…