Search Results for author:
Found 24 papers, 4 papers with code
CPPF: A contextual and post-processing-free model for automatic speech recognition
To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model.
SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection
Some scene fake audio detection benchmark results on the SceneFake dataset are reported in this paper.
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization
To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.
Fully Automated End-to-End Fake Audio Detection
The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure.
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
Reducing language context confusion for end-to-end code-switching automatic speech recognition
We propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint (EC) Theory.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues
In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents.
Continual Learning for Fake Audio Detection
However, fine-tuning leads to performance degradation on previous data.
Half-Truth: A Partially Fake Audio Detection Dataset
Therefore, this paper develops such a dataset for half-truth audio detection (HAD).
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization
It takes a lot of computation and time to predict the blank tokens, but only the non-blank tokens will appear in the final output sequence.
TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition
To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT), which improves the performance and accelerating the convergence of the NAR model by learning prior knowledge from a parameters-sharing AR model.
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
Based on this idea, we propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once).
Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition
In this paper, we propose a decoupled transformer model to use monolingual paired data and unpaired text data to alleviate the problem of code-switching data shortage.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition
Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model.
Deep imitator: Handwriting calligraphy imitation via deep attention networks
Calligraphy imitation (CI) from a handful of target handwriting samples is such a challenging task that most of the existing writing style analysis or handwriting generation methods do not exhibit satisfactory performance.
Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition
To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition
Without beam-search, the one-pass propagation much reduces inference time cost of LASO.
Adversarial Transfer Learning for Punctuation Restoration
The other is that POS tags are provided by an external POS tagger.
Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition.
Synchronous Transformers for End-to-End Speech Recognition
Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately.
Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data
To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence.
Self-Attention Transducers for End-to-End Speech Recognition
Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance.
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition
Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial.
