相关论文: UniWhisper: Efficient Continual Multi-task Trainin…

Encoder-decoder models have achieved remarkable success in speech and text tasks, yet efficiently adapting these models to diverse uni/multi-modal scenarios remains an open challenge. In this paper, we propose Whisper-UT, a unified and…

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…

Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text…

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

The speech field is evolving to solve more challenging scenarios, such as multi-channel recordings with multiple simultaneous talkers. Given the many types of microphone setups out there, we present the UniX-Encoder. It's a universal…

Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations for music and environmental sound. This forces downstream…

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited…

Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly…

Voice conversion systems have made significant advancements in terms of naturalness and similarity in common voice conversion tasks. However, their performance in more complex tasks such as cross-lingual voice conversion and expressive…

We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data in one language and directly applied to inputs of the same…

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

Large-scale in-the-wild speech datasets have become more prevalent in recent years due to increased interest in models that can learn useful features from unlabelled data for tasks such as speech recognition or synthesis. These datasets…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

Large Language models (LLM) have demonstrated the capability to handle a variety of generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific approaches, leverages LLM techniques to generate multiple types…

Many speech applications require understanding aspects beyond the words being spoken, such as recognizing emotion, detecting whether the speaker is wearing a mask, or distinguishing real from synthetic speech. In this work, we introduce a…

Whisper, despite being trained on 680K hours of web-scaled audio data, faces difficulty in recognising rare words like domain-specific terms, with a solution being contextual biasing through prompting. To improve upon this method, in this…

Audio-driven 3D facial animation aims to map input audio to realistic facial motion. Despite significant progress, limitations arise from inconsistent 3D annotations, restricting previous models to training on specific annotations and…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and…

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…