相关论文: Speech is Silver, Silence is Golden: What do ASVsp…

Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing why this occurs on a technological level. To our knowledge, we present the first layerwise…

ASVspoof5, the fifth edition of the ASVspoof series, is one of the largest global audio security challenges. It aims to advance the development of countermeasure (CM) to discriminate bonafide and spoofed speech utterances. In this paper, we…

Self-supervised learning has shown great success in Speech Recognition. However, it has been observed that finetuning all layers of the learned model leads to lower performance compared to resetting top layers. This phenomenon is attributed…

This paper describes the Speech Technology Center (STC) antispoofing systems submitted to the ASVspoof 2019 challenge. The ASVspoof2019 is the extended version of the previous challenges and includes 2 evaluation conditions: logical access…

Our prior experiments show that humans and machines seem to employ different approaches to speaker discrimination, especially in the presence of speaking style variability. The experiments examined read versus conversational speech.…

This paper presents an end-to-end model designed to improve automatic speech recognition (ASR) for a particular speaker in a crowded, noisy environment. The model utilizes a single-channel speech enhancement module that isolates the…

Deep learning based speech enhancement has made rapid development towards improving quality, while models are becoming more compact and usable for real-time on-the-edge inference. However, the speech quality scales directly with the model…

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…

In order to evaluate the performance of the attention based neural ASR under noisy conditions, the current trend is to present hours of various noisy speech data to the model and measure the overall word/phoneme error rate (W/PER). In…

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

In psycholinguistic modeling, surprisal from larger pre-trained language models has been shown to be a poorer predictor of naturalistic human reading times. However, it has been speculated that this may be due to data leakage that caused…

When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a…

In this paper, we present an improved model for voicing silent speech, where audio is synthesized from facial electromyography (EMG) signals. To give our model greater flexibility to learn its own input features, we directly use EMG signals…

Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To…

Models that can handle a wide range of speakers and acoustic conditions are essential in speech emotion recognition (SER). Often, these models tend to show mixed results when presented with speakers or acoustic conditions that were not…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…