Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving RNN Transducer With Target Speaker Extraction and Neural Uncertainty Estimation
122
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech extraction and Recurrent Neural Network Transducer (RNN-T). To stabilize the joint-training, we propose a multi-stage training strategy that pre-trains and fine-tunes each module in the system before joint-training. Meanwhile, speaker identity and speech enhancement uncertainty measures are proposed to compensate for residual noise and artifacts from the target speech extraction module. Compared to a recognizer fine-tuned with a target speech extraction model, our experiments show that adding the neural uncertainty module significantly reduces 17% relative Character Error Rate (CER) on multi-speaker signals with background noise. The multi-condition experiments indicate that our method can achieve 9% relative performance gain in the noisy condition while maintaining the performance in the clean condition.
rate research
Read More
To extract the voice of a target speaker when mixed with a variety of other sounds, such as white and ambient noises or the voices of interfering speakers, we extend the Transformer network to attend the most relevant information with respect to the target speaker given the characteristics of his or her voices as a form of contextual information. The idea has a natural interpretation in terms of the selective attention theory. Specifically, we propose two models to incorporate the voice characteristics in Transformer based on different insights of where the feature selection should take place. Both models yield excellent performance, on par or better than published state-of-the-art models on the speaker extraction task, including separating speech of novel speakers not seen during training.
One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training. However, available one-shot voice conversion approaches are not stable for unseen speakers as the speaker embedding extracted from one utterance of an unseen speaker is not reliable. In this paper, we propose a deep discriminative speaker encoder to extract speaker embedding from one utterance more effectively. Specifically, the speaker encoder first integrates residual network and squeeze-and-excitation network to extract discriminative speaker information in frame level by modeling frame-wise and channel-wise interdependence in features. Then attention mechanism is introduced to further emphasize speaker related information via assigning different weights to frame level speaker information. Finally a statistic pooling layer is used to aggregate weighted frame level speaker information to form utterance level speaker embedding. The experimental results demonstrate that our proposed speaker encoder can improve the robustness of one-shot voice conversion for unseen speakers and outperforms baseline systems in terms of speech quality and speaker similarity.
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (LAS). In this paper, we present various improvements to NT. Specifically, we look at increasing the window over which NT computes attention, mainly by looking backwards in time so the model still remains online. In addition, we explore initializing a NT model from a LAS-trained model so that it is guided with a better alignment. Finally, we explore including stronger language models such as using wordpiece models, and applying an external LM during the beam search. On a Voice Search task, we find with these improvements we can get NT to match the performance of LAS.
Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified context vector which takes into account total attention across encoder units as well, giving us a new cross-attention mechanism. Apart from this, we also investigate a multi-task learning approach for jointly estimating speaker height and age. We train and test our model on the TIMIT corpus. Our model outperforms several approaches in the literature. We achieve a root mean square error (RMSE) of 6.92cm and6.34cm for male and female heights respectively and RMSE of 7.85years and 8.75years for male and females ages respectively. By tracking the attention weights allocated to different phones, we find that Vowel phones are most important whistlestop phones are least important for the estimation task.
Nowadays, there is a strong need to deploy the target speaker separation (TSS) model on mobile devices with a limitation of the model size and computational complexity. To better perform TSS for mobile voice communication, we first make a dual-channel dataset based on a specific scenario, LibriPhone. Specifically, to better mimic the real-case scenario, instead of simulating from the single-channel dataset, LibriPhone is made by simultaneously replaying pairs of utterances from LibriSpeech by two professional artificial heads and recording by two built-in microphones of the mobile. Then, we propose a lightweight time-frequency domain separation model, LSTM-Former, which is based on the LSTM framework with source-to-noise ratio (SI-SNR) loss. For the experiments on Libri-Phone, we explore the dual-channel LSTMFormer model and a single-channel version by a random single channel of Libri-Phone. Experimental result shows that the dual-channel LSTM-Former outperforms the single-channel LSTMFormer with relative 25% improvement. This work provides a feasible solution for the TSS task on mobile devices, playing back and recording multiple data sources in real application scenarios for getting dual-channel real data can assist the lightweight model to achieve higher performance.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
