Large-scale pretrained models using self-supervised learning have reportedly improved the performance of speech anti-spoofing.
This paper focuses on speaker diarization and proposes to conduct the above bi-directional knowledge transfer alternately.
In this paper, we present an incremental domain adaptation technique to prevent catastrophic forgetting for an end-to-end automatic speech recognition (ASR) model.
Finally, to improve online diarization, our method improves the buffer update method and revisits the variable chunk-size training of EEND.
We propose a fundamental theory on ensemble learning that answers the central question: what factors make an ensemble system good or bad?
Due to the lack of any annotated real conversational dataset, EEND is usually pretrained on a large-scale simulated conversational dataset first and then adapted to the target real dataset.
An onomatopoeic word, which is a character sequence that phonetically imitates a sound, is effective in expressing characteristics of sound such as duration, pitch, and timbre.
With simulated and real-recorded datasets, we demonstrated that the proposed method outperformed conventional EEND when a multi-channel input was given while maintaining comparable performance with a single-channel input.
This makes it possible to produce diarization results of a large number of speakers for the whole recording even if the number of output speakers for each subsequence is limited.
Diarization results are then estimated as dot products of the attractors and embeddings.
To evaluate our proposed method, we conduct the experiments of model adaptation using labeled and unlabeled data.
In this paper, we present a conditional multitask learning method for end-to-end neural speaker diarization (EEND).
This paper provides a detailed description of the Hitachi-JHU system that was submitted to the Third DIHARD Speech Diarization Challenge.
We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech.
Speaker Diarization Sound Audio and Speech Processing
Clustering-based diarization methods partition frames into clusters of the number of speakers; thus, they typically cannot handle overlapping speech because each frame is assigned to one speaker.
Users of social networking services often share their emotions via multi-modal content, usually images paired with text embedded in them.
It is also a problem that the offline GSS is an utterance-wise algorithm so that it produces latency according to the length of the utterance.
We also showed that our framework achieved CER of 21. 8 %, which is only 2. 1 percentage points higher than the CER in headset microphone-based transcription.
This paper proposes a novel online speaker diarization algorithm based on a fully supervised self-attention mechanism (SA-EEND).
Speaker diarization is an essential step for processing multi-speaker audio.
End-to-end speaker diarization for an unknown number of speakers is addressed in this paper.
no code implementations • 20 Apr 2020 • Shinji Watanabe, Michael Mandel, Jon Barker, Emmanuel Vincent, Ashish Arora, Xuankai Chang, Sanjeev Khudanpur, Vimal Manohar, Daniel Povey, Desh Raj, David Snyder, Aswin Shanmugam Subramanian, Jan Trmal, Bar Ben Yair, Christoph Boeddeker, Zhaoheng Ni, Yusuke Fujita, Shota Horiguchi, Naoyuki Kanda, Takuya Yoshioka, Neville Ryant
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6).
However, the clustering-based approach has a number of problems; i. e., (i) it is not optimized to minimize diarization errors directly, (ii) it cannot handle speaker overlaps correctly, and (iii) it has trouble adapting their speaker embedding models to real audio recordings with speaker overlaps.
Our proposed method combined with i-vector speaker embeddings ultimately achieved a WER that differed by only 2. 1 % from that of TS-ASR given oracle speaker embeddings.
Our method was even better than that of the state-of-the-art x-vector clustering-based method.
Ranked #2 on Speaker Diarization on CALLHOME
To realize such a model, we formulate the speaker diarization problem as a multi-label classification problem, and introduces a permutation-free objective function to directly minimize diarization errors without being suffered from the speaker-label permutation problem.
Ranked #6 on Speaker Diarization on CALLHOME
In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR).
In this paper, we present Hitachi and Paderborn University's joint effort for automatic speech recognition (ASR) in a dinner party scenario.
In this paper, we address the personalization problem, which involves adapting to the user's domain incrementally using a very limited number of samples.
However, in these DML studies, there were no equitable comparisons between features extracted from a DML-based network and those from a softmax-based network.