Related papers: Voice Timbre Attribute Detection with Compact and …

In this paper, we learn disentangled representations of timbre and pitch for musical instrument sounds. We adapt a framework based on variational autoencoders with Gaussian mixture latent distributions. Specifically, we use two separate…

Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted agent interactions and dropped calls. We present a lightweight approach that extracts 15 temporal features from the speech…

In this paper, we propose Vo-Ve, a novel voice-vector embedding that captures speaker identity. Unlike conventional speaker embeddings, Vo-Ve is explainable, as it contains the probabilities of explicit voice attribute classes. Through…

Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to…

Jitter and shimmer measurements have shown to be carriers of voice quality and prosodic information which enhance the performance of tasks like speaker recognition, diarization or automatic speech recognition (ASR). However, such features…

In this study, we produce a geometrically scaled perceptual timbre space from dissimilarity ratings of subtractive synthesized sounds and correlate the resulting dimensions with a set of acoustic descriptors. We curate a set of 15 sounds,…

Target sound detection (TSD) aims to detect the target sound from a mixture audio given the reference information. Previous methods use a conditional network to extract a sound-discriminative embedding from the reference audio, and then use…

Audio-Visual Target Speaker Extraction (AVTSE) aims to isolate a target speaker's voice in a multi-speaker environment with visual cues as auxiliary. Most of the existing AVTSE methods encode visual and audio features simultaneously,…

Keyword spotting (KWS) and speaker verification (SV) have been studied independently although it is known that acoustic and speaker domains are complementary. In this paper, we propose a multi-task network that performs KWS and SV…

This study employs deep learning techniques to explore four speaker profiling tasks on the TIMIT dataset, namely gender classification, accent classification, age estimation, and speaker identification, highlighting the potential and…

Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors…

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…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches,…

As a neurophysiological response to threat or adverse conditions, stress can affect cognition, emotion and behaviour with potentially detrimental effects on health in the case of sustained exposure. Since the affective content of speech is…

Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach…

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Recent advancements in deep learning have led to drastic improvements in speech segregation models. Despite their success and growing applicability, few efforts have been made to analyze the underlying principles that these networks learn…

Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech recognition(AV-ASR). Our primary task is to learn a mapping…

Voice activity detection is the task of detecting speech regions in a given audio stream or recording. First, we design a neural network combining trainable filters and recurrent layers to tackle voice activity detection directly from the…