相关论文: Enhancing Speaker Verification with w2v-BERT 2.0 a…

Transformer-based language models have become a key building block for natural language processing. While these models are extremely accurate, they can be too large and computationally intensive to run on standard deployments. A variety of…

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties…

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…

In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…

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…

We introduce an extensive dataset for multilingual probing of morphological information in language models (247 tasks across 42 languages from 10 families), each consisting of a sentence with a target word and a morphological tag as the…

Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a…

Self-supervised learning (SSL) has achieved notable success in many speech processing tasks, but the large model size and heavy computational cost hinder the deployment. Knowledge distillation trains a small student model to mimic the…

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments…

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However,…

The convolutional neural network (CNN) based approaches have shown great success for speaker verification (SV) tasks, where modeling long temporal context and reducing information loss of speaker characteristics are two important challenges…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

The performances of the automatic speaker verification (ASV) systems degrade due to the reduction in the amount of speech used for enrollment and verification. Combining multiple systems based on different features and classifiers…

Speaker verification (SV) provides billions of voice-enabled devices with access control, and ensures the security of voice-driven technologies. As a type of biometrics, it is necessary that SV is unbiased, with consistent and reliable…

The state-of-art approach to speaker verification involves the extraction of discriminative embeddings like x-vectors followed by a generative model back-end using a probabilistic linear discriminant analysis (PLDA). In this paper, we…

Training data cleaning is a new application for generative model-based speech restoration (SR). This paper introduces Miipher-2, an SR model designed for million-hour scale data, for training data cleaning for large-scale generative models…

While Wav2Vec 2.0 has been proposed for speech recognition (ASR), it can also be used for speech emotion recognition (SER); its performance can be significantly improved using different fine-tuning strategies. Two baseline methods, vanilla…