Related papers: Discrimination loss vs. SRT: A model-based approac…

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluating…

While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Over half of US adults with Alzheimer disease and related dementias remain undiagnosed, and speech-based screening offers a scalable detection approach. We compared large language model adaptation strategies for dementia detection using the…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

The common target speech separation directly estimate the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation model (MTSS) to simultaneously extract each…

Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteristics of the target speaker. One major difficulty of target…

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

Usually, hearing impaired people use hearing aids which are implemented with speech enhancement algorithms. Estimation of speech and estimation of nose are the components in single channel speech enhancement system. The main objective of…

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines…

There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and COMET. These metrics have been used to evaluate simultaneous…

This paper explores speculative speech recognition (SSR), where we empower conventional automatic speech recognition (ASR) with speculation capabilities, allowing the recognizer to run ahead of audio. We introduce a metric for measuring SSR…

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…

Speaker-role diarization (RD), such as doctor vs. patient or lawyer vs. client, is practically often more useful than conventional speaker diarization (SD), which assigns only generic labels (speaker-1, speaker-2). The state-of-the-art…

Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data. In these cases, we wish to go…

Traditional audiometry often provides an incomplete characterization of the functional impact of hearing loss on speech understanding, particularly for supra-threshold deficits common in presbycusis. This motivates the development of more…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Objective: Currently, only behavioral speech understanding tests are available, which require active participation of the person being tested. As this is infeasible for certain populations, an objective measure of speech intelligibility is…

Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for…

The effect of hearing impairment on speech perception was described by Plomp (1978) as a sum of a loss of class A, due to signal attenuation, and a loss of class D, due to signal distortion. While a loss of class A can be compensated by…