Related papers: XANE: eXplainable Acoustic Neural Embeddings

Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express…

Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or concatenation of reference phone embedding and actual…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local,…

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

Whisper, as a form of speech, is not sufficiently addressed by mainstream speech applications. This is due to the fact that systems built for normal speech do not work as expected for whispered speech. A first step to building a speech…

Traditional Query-by-Example (QbE) speech search approaches usually use methods based on frame-level features, while state-of-the-art approaches tend to use models based on acoustic word embeddings (AWEs) to transform variable length audio…

Semantic embeddings play a crucial role in natural language-based information retrieval. Embedding models represent words and contexts as vectors whose spatial configuration is derived from the distribution of words in large text corpora.…

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

The performance of voice-controlled systems is usually influenced by accented speech. To make these systems more robust, the frontend accent recognition (AR) technologies have received increased attention in recent years. As accent is a…

We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding…

Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

An ideal audio retrieval system efficiently and robustly recognizes a short query snippet from an extensive database. However, the performance of well-known audio fingerprinting systems falls short at high signal distortion levels. This…

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce…

This paper introduces a novel approach to speech restoration by integrating a context-related conditioning strategy. Specifically, we employ the diffusion-based generative restoration model, UNIVERSE++, as a backbone to evaluate the…

Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term…

Speaker embedding extractors significantly influence the performance of clustering-based speaker diarisation systems. Conventionally, only one embedding is extracted from each speech segment. However, because of the sliding window approach,…

Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the…