Related papers: AISTAT lab system for DCASE2025 Task6: Language-ba…

This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data from different…

This technical report describes the details of our TASK1A submission of the DCASE2021 challenge. The goal of the task is to design an audio scene classification system for device-imbalanced datasets under the constraints of model…

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…

More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels…

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…

In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses…

Matching raw audio signals with textual descriptions requires understanding the audio's content and the description's semantics and then drawing connections between the two modalities. This paper investigates a hybrid retrieval system that…

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual…

As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This…

Audio tagging aims to perform multi-label classification on audio chunks and it is a newly proposed task in the Detection and Classification of Acoustic Scenes and Events 2016 (DCASE 2016) challenge. This task encourages research efforts to…

Environmental sound analysis is currently getting more and more attentions. In the domain, acoustic scene classification and acoustic event classification are two closely related tasks. In this letter, a two-stage method is proposed for the…

Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…

A central problem in building effective sound event detection systems is the lack of high-quality, strongly annotated sound event datasets. For this reason, Task 4 of the DCASE 2024 challenge proposes learning from two heterogeneous…

Mainstream Audio Analytics models are trained to learn under the paradigm of one class label to many recordings focusing on one task. Learning under such restricted supervision limits the flexibility of models because they require labeled…

Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks. However, existing unified foundations often struggle to…

This paper presents our MSXF TTS system for Task 3.1 of the Audio Deep Synthesis Detection (ADD) Challenge 2022. We use an end to end text to speech system, and add a constraint loss to the system when training stage. The end to end TTS…

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are…