相关论文: On-demand compute reduction with stochastic wav2ve…

Self-supervised learning, such as with the wav2vec 2.0 framework significantly improves the accuracy of end-to-end automatic speech recognition (ASR). Wav2vec 2.0 has been applied to single-channel end-to-end ASR models. In this work, we…

Wav2vec2 has achieved success in applying Transformer architecture and self-supervised learning to speech recognition. Recently, these have come to be used not only for speech recognition but also for the entire speech processing. This…

Projection-based reduced-order models (PROMs) have demonstrated accuracy, reliability, and robustness in approximating high-dimensional, differential equation-based computational models across many applications. For this reason, it has been…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

Weight averaging has become a standard technique for enhancing model performance. However, methods such as Stochastic Weight Averaging (SWA) and Latest Weight Averaging (LAWA) often require manually designed procedures to sample from the…

This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…

This work evaluates the compression techniques on ConvNeXt models in image classification tasks using the CIFAR-10 dataset. Structured pruning, unstructured pruning, and dynamic quantization methods are evaluated to reduce model size and…

The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) -- the core metric for Whisper-style tokenizers -- as the…

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the…

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

Self-supervised learning (SSL) models like WavLM can be effectively utilized when building speaker diarization systems but are often large and slow, limiting their use in resource constrained scenarios. Previous studies have explored…

Stuttering is a varied speech disorder that harms an individual's communication ability. Persons who stutter (PWS) often use speech therapy to cope with their condition. Improving speech recognition systems for people with such non-typical…

Modern sensors produce increasingly rich streams of high-resolution data. Due to resource constraints, machine learning systems discard the vast majority of this information via resolution reduction. Compressed-domain learning allows models…

Recent studies have shown how self-supervised models can produce accurate speech quality predictions. Speech representations generated by the pre-trained wav2vec 2.0 model allows constructing robust predicting models using small amounts of…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

This study evaluates the performance of three advanced speech encoder models, Wav2Vec 2.0, XLS-R, and Whisper, in speaker identification tasks. By fine-tuning these models and analyzing their layer-wise representations using SVCCA, k-means…

Modeling latent representations in a hyperspherical space has proven effective for capturing directional similarities in high-dimensional text data, benefiting topic modeling. Variational autoencoder-based neural topic models (VAE-NTMs)…

We present the development of a semi-supervised regression method using variational autoencoders (VAE), which is customized for use in soft sensing applications. We motivate the use of semi-supervised learning considering the fact that…

Weighted-sum energy efficiency (WSEE) is a key performance metric in heterogeneous networks, where the nodes may have different energy efficiency (EE) requirements. Nevertheless, WSEE maximization is a challenging problem due to its…

Target speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture. The popular training objective for most prior TSE networks is to enhance reconstruction performance of extracted speech waveform.…