相关论文: Precise Detection of Speech Endpoints Dynamically:…

Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly…

The Automatic Speaker Verification systems have potential in biometrics applications for logical control access and authentication. A lot of things happen to be at stake if the ASV system is compromised. The preliminary work presents a…

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder. The effectiveness of the WaveNet vocoder for generating natural speech from acoustic…

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic…

Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency,…

ASR endpointing (EP) plays a major role in delivering a good user experience in products supporting human or artificial agents in human-human/machine conversations. Transducer-based ASR (T-ASR) is an end-to-end (E2E) ASR modelling technique…

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of…

This work focuses on online dereverberation for hearing devices using the weighted prediction error (WPE) algorithm. WPE filtering requires an estimate of the target speech power spectral density (PSD). Recently deep neural networks (DNNs)…

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

Many end-to-end Automatic Speech Recognition (ASR) systems still rely on pre-processed frequency-domain features that are handcrafted to emulate the human hearing. Our work is motivated by recent advances in integrated learnable feature…

Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Target speech extraction (TSE) focuses on extracting the speech of a specific target speaker from a mixture of signals. Existing TSE models typically utilize static embeddings as conditions for extracting the target speaker's voice.…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody…

Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe deterrent to the inclusive adoption of ASR. In this work, we…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…