Related papers: Evaluation of Speech Representations for MOS predi…

Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets…

We analyze the impact of speaker adaptation in end-to-end automatic speech recognition models based on transformers and wav2vec 2.0 under different noise conditions. By including speaker embeddings obtained from x-vector and ECAPA-TDNN…

In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with global context followed by channel…

This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize ``who spoke what'' with low latency even when multiple people are speaking simultaneously. Our model is based on token-level…

Current state-of-the-art speech recognition models are trained to map acoustic signals into sub-lexical units. While these models demonstrate superior performance, they remain vulnerable to out-of-distribution conditions such as background…

This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…

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…

We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding…

Deep neural network approaches to speaker verification have proven successful, but typical computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for embedded applications. In this work, we present a two-stage…

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

Macroscopic intelligibility models predict the expected human word-error-rate for a given speech-in-noise stimulus. In contrast, microscopic intelligibility models aim to make fine-grained predictions about listeners' perception, e.g.…

While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based…

Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between…

This paper introduces BWSNet, a model that can be trained from raw human judgements obtained through a Best-Worst scaling (BWS) experiment. It maps sound samples into an embedded space that represents the perception of a studied attribute.…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Self-supervised learning (SSL) models like Wav2Vec2, HuBERT, and WavLM have been widely used in speech processing. These transformer-based models consist of multiple layers, each capturing different levels of representation. While prior…

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

This paper proposes the target speaker enhancement based speaker verification network (TASE-SVNet), an all neural model that couples target speaker enhancement and speaker embedding extraction for robust speaker verification (SV).…