Related papers: VADOI:Voice-Activity-Detection Overlapping Inferen…
In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for…
We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths…
Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…
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…
Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel…
Cross-modal associations between voice and face from a person can be learnt algorithmically, which can benefit a lot of applications. The problem can be defined as voice-face matching and retrieval tasks. Much research attention has been…
The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech…
This paper presents a comparison of a traditional hybrid speech recognition system (kaldi using WFST and TDNN with lattice-free MMI) and a lexicon-free end-to-end (TensorFlow implementation of multi-layer LSTM with CTC training) models for…
Long-form speech recognition with large encoder-decoder models such as Whisper often exhibit hallucinations, repetition loops, and content omissions. These errors can accumulate and be further amplified when the previous segment's…
We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed…
Recent advances in deep learning based large vocabulary con- tinuous speech recognition (LVCSR) invoke growing demands in large scale speech transcription. The inference process of a speech recognizer is to find a sequence of labels whose…
Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware…
End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words…
Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the…
The choice of an optimal time-frequency resolution is usually a difficult but important step in tasks involving speech signal classification, e.g., speech anti-spoofing. The variations of the performance with different choices of…
This paper describes a submission to the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2) 2026, which addresses component-level deepfake detection using the CompSpoofV2 dataset, where speech and environmental sounds…