Related papers: SSHR: Leveraging Self-supervised Hierarchical Repr…

While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing…

Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We…

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by…

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Driven by large scale datasets and LLM based architectures, automatic speech recognition (ASR) systems have achieved remarkable improvements in accuracy. However, challenges persist for domain-specific terminology, and short utterances…

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach…

Large Language Models (LLMs) possess encompassing capabilities that can process diverse language-related tasks. However, finetuning on LLMs will diminish this general skills and continual finetuning will further cause severe degradation on…

Approximately half of the world's population is multilingual, making multilingual ASR (MASR) essential. Deploying multiple monolingual models is challenging when the ground-truth language is unknown in advance. This motivates research…

Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech recognition (ASR) under high-resource conditions. However, existing benchmarks…

This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-"maybe"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture…

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, there is limited research on the specific meanings of the…

When dealing with overlapped speech, the performance of automatic speech recognition (ASR) systems substantially degrades as they are designed for single-talker speech. To enhance ASR performance in conversational or meeting environments,…

We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Automatic speech recognition (ASR) of multi-channel multi-speaker overlapped speech remains one of the most challenging tasks to the speech community. In this paper, we look into this challenge by utilizing the location information of…