Related papers: BEST-STD2.0: Balanced and Efficient Speech Tokeniz…
Stuttering is a varied speech disorder that harms an individual's communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition systems for people with such non-typical…
Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…
Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in…
Most current speech enhancement (SE) methods recover clean speech from noisy inputs by directly estimating time-frequency masks or spectrums. However, these approaches often neglect the distinct attributes, such as semantic content and…
This paper describes the current TT\"U speech transcription system for Estonian speech. The system is designed to handle semi-spontaneous speech, such as broadcast conversations, lecture recordings and interviews recorded in diverse…
Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification…
In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech…
In this paper, we propose an online speaker diarization system based on Relation Network, named RenoSD. Unlike conventional diariztion systems which consist of several independently-optimized modules, RenoSD implements…
State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…
Query term matching with document term matching is the basic function of any best effort Information Retrieval models like Vector Space Model. In our problem of SMS based Information Systems we expect common people to participate in…
The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete,…
For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…
This paper addresses the challenging scenario for the distant-talking control of a music playback device, a common portable speaker with four small loudspeakers in close proximity to one microphone. The user controls the device through…
Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as…
Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD…
Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…
This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search. However, while stance is easily…
Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…