Related papers: Implicit spoken language diarization
The objective of this work is speaker diarisation of speech recordings 'in the wild'. The ability to determine speech segments is a crucial part of diarisation systems, accounting for a large proportion of errors. In this paper, we present…
Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…
Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…
Recently, a method for synthesizing foreign-accented speech only with native speech data using discrete tokens obtained from self-supervised learning (SSL) models was proposed. Considering limited availability of accented speech data, this…
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…
The extensive memory footprint of language model (LM) fine-tuning poses a challenge for both researchers and practitioners. LMs use an embedding matrix to represent extensive vocabularies, forming a substantial proportion of the model…
Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with…
Large language models (LLMs), trained on large-scale text, have recently attracted significant attention for their strong performance across many tasks. Motivated by this, we investigate whether a text-trained LLM can help localize fake…
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…
Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…
This paper describes a system that generates speaker-annotated transcripts of meetings by using a microphone array and a 360-degree camera. The hallmark of the system is its ability to handle overlapped speech, which has been an unsolved…
The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…
Spoken Language Models (SLMs) have emerged as a promising paradigm for speech synthesis by bypassing explicit grapheme-to-phoneme pipelines. However, their effectiveness in low-resource languages remains fundamentally limited by the…
Deep acoustic models represent linguistic information based on massive amounts of data. Unfortunately, for regional languages and dialects such resources are mostly not available. However, deep acoustic models might have learned linguistic…
Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem. Although the standard diarization systems can achieve satisfactory results in various scenarios, they…
Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs diarization by first separating the speakers and then applying…
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…
The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The…
Collecting high-quality training data is essential for fine-tuning Large Language Models (LLMs). However, acquiring such data is often costly and time-consuming, especially for non-English languages such as Italian. Recently, researchers…