Search Results for author:
Found 10 papers, 2 papers with code
PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings
A major drawback of supervised speech separation (SSep) systems is their reliance on synthetic data, leading to poor real-world generalization.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Dialect Adaptation and Data Augmentation for Low-Resource ASR: TalTech Systems for the MADASR 2023 Challenge
This paper describes Tallinn University of Technology (TalTech) systems developed for the ASRU MADASR 2023 Challenge.
Collar-aware Training for Streaming Speaker Change Detection in Broadcast Speech
Instead, the proposed method uses an objective function which encourages the model to predict a single positive label within a specified collar.
Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challenge
For the unconstrained task, we relied on both externally available pretrained models as well as external data: the multilingual XLSR-53 wav2vec2. 0 model was finetuned on the VoxLingua107 corpus for the language recognition task, and finally finetuned on the provided target language training data, augmented with CommonVoice data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Improving Language Identification of Accented Speech
Language identification from speech is a common preprocessing step in many spoken language processing systems.
VoxLingua107: a Dataset for Spoken Language Recognition
Speech activity detection and speaker diarization are used to extract segments from the videos that contain speech.
Robust Training of Vector Quantized Bottleneck Models
We show that the codebook learning can suffer from poor initialization and non-stationarity of clustered encoder outputs.
Advanced Rich Transcription System for Estonian Speech
Out-of-vocabulary words are recovered using a phoneme n-gram based decoding subgraph and a FST-based phoneme-to-grapheme model.
Weakly Supervised Training of Speaker Identification Models
The method uses speaker diarization to find unique speakers in each recording, and i-vectors to project the speech of each speaker to a fixed-dimensional vector.
Low-Resource Neural Headline Generation
Recent neural headline generation models have shown great results, but are generally trained on very large datasets.
