Related papers: TI-ASU: Toward Robust Automatic Speech Understandi…

State-of-the-art Active Speaker Detection (ASD) approaches heavily rely on audio and facial features to perform, which is not a sustainable approach in wild scenarios. Although these methods achieve good results in the standard…

We present a novel approach to multilingual audio-visual speech recognition tasks by introducing a single model on a multilingual dataset. Motivated by a human cognitive system where humans can intuitively distinguish different languages…

Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the…

Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often…

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between…

Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems. Existing methods primarily focus on aligning…

Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental…

Spoken Language Understanding (SLU), which aims to extract user semantics to execute downstream tasks, is a crucial component of task-oriented dialog systems. Existing SLU datasets generally lack sufficient diversity and complexity, and…

Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

Inverse text normalization (ITN) is crucial for converting spoken-form into written-form, especially in the context of automatic speech recognition (ASR). While most downstream tasks of ASR rely on written-form, ASR systems often output…

Unsupervised speech recognition (ASR-U) is the problem of learning automatic speech recognition (ASR) systems from unpaired speech-only and text-only corpora. While various algorithms exist to solve this problem, a theoretical framework is…

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes…

We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language…

In this paper, we investigate the semi-supervised joint training of text to speech (TTS) and automatic speech recognition (ASR), where a small amount of paired data and a large amount of unpaired text data are available. Conventional…