Merge branch 'source' into blog

shinjiwlab · Oct 5, 2023 · 90602ea · 90602ea
2 parents f72ba6e + e2fd0c0
commit 90602ea
Show file tree

Hide file tree

Showing 27 changed files with 3,227 additions and 73 deletions.
diff --git a/_bibliography/papers.bib b/_bibliography/papers.bib
@@ -14,6 +14,169 @@ @string{WASPAA
 @string{APSIPA = {Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)}}
 @string{ICML = {Proceedings of the International Conference on Machine Learning (ICML)}}
 @string{ICLR = {Proceedings of the International Conference on Learning Representations (ICLR)}}
+@string{NeurIPS = {Proceedings of the Conference on Neural Information Processing Systems}}
+
+
+@inproceedings{chou2023evaluating,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={Evaluating Self-supervised Speech Models on a Taiwanese Hokkien Corpus},
+    author={Yi-Hui Chou and Kalvin Chang and Meng-Ju Wu and Winston Ou and Alice Wen-Hsin Bi and Carol Yang and Bryan Y. Chen and Rong-Wei Pai and Po-Yen Yeh and Jo-Peng Chiang and Lu-Tshiann Phoann and Winnie Chang and Chenxuan Cui and Noel Chen and Jiatong Shi},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+
+}
+
+@inproceedings{huang2023singing,
+    abbr={SVC},
+    abbr_publisher={ASRU},
+    title={The Singing Voice Conversion Challenge 2023},
+    author={Wen-Chin Huang and Lester Phillip Violeta and Songxiang Liu and Jiatong Shi and Tomoki Toda},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{shiohara2023domain,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={Domain Adaptation by Data Distribution Matching via Submodularity for Speech Recognition},
+    author={Yusuke Shinohara and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{kano2023summarize,
+    abbr={Summarization&ST},
+    abbr_publisher={ASRU},
+    title={Summarize while Translating: Universal Model with Parallel Decoding for Summarization and Translation},
+    author={Takatomo Kano and Atsunori Ogawa and Marc Delcroix and Kohei Matsuura and Takanori Ashihara and William Chen and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{li2023yodas,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={YODAS: Youtube-Oriented Dataset for Audio and Speech},
+    author={Xinjian Li and Shinnosuke Takamichi and Takaaki Saeki and William Chen and Sayaka Shiota and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{kohei2023single,
+    abbr={SE&SS},
+    abbr_publisher={ASRU},
+    title={A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction},
+    author={Kohei Saijo and Wangyou Zhang and Zhong-Qiu Wang and Shinji Watanabe and Tetsunori Kobayashi and Tetsuji Ogawa},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{wang2023torchaudio,
+    abbr={ASR&SSL},
+    abbr_publisher={ASRU},
+    title={TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch},
+    author={Jeff Hwang and Moto Hira and Caroline Chen and Xiaohui Zhang and Zhaoheng Ni and Guangzhi Sun and Pingchuan Ma and Ruizhe Huang and Vineel Pratap and Yuekai Zhang and Anurag Kumar and Chin-Yun Yu and Chuang Zhu and Chunxi Liu and Jacob Kahn and Mirco Ravanelli and Peng Sun and Shinji Watanabe and Yangyang Shi and Yumeng Tao},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{zhang2023toward,
+    abbr={SE},
+    abbr_publisher={ASRU},
+    title={Toward Universal Speech Enhancement For Diverse Input Conditions},
+    author={Wangyou Zhang and Kohei Saijo and Zhong-Qiu Wang and Shinji Watanabe and Yanmin Qian},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{shi2023findings,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond},
+    author={Jiatong Shi and William Chen and Dan Berrebbi and Hsiu-Hsuan Wang and Wei Ping Huang and En Pei Hu and ho lam Chung and Xuankai Chang and Yuxun Tang and Shang-Wen Li and Abdelrahman Mohamed and Hung-yi Lee and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{chen2023joint,
+    abbr={SSL},
+    abbr_publisher={ASRU},
+    title={Joint Prediction and Denoising for Large-Scale Multilingual Self-Supervised Learning},
+    author={William Chen and Jiatong Shi and Brian Yan and Dan Berrebbi and Wangyou Zhang and Yifan Peng and Xuankai Chang and Soumi Maiti and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{someki2023segment,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference},
+    author={Masao Someki and Nicholas Eng and Yosuke Higuchi and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{peng2023reproducing,
+    abbr={ASR&ST},
+    abbr_publisher={ASRU},
+    title={Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data},
+    author={Yifan Peng and Jinchuan Tian and Brian Yan and Dan Berrebbi and Xuankai Chang and Xinjian Li and Jiatong Shi and Siddhant Arora and William Chen and Roshan Sharma and Wangyou Zhang and Yui Sudo and Muhammad Shakeel and Jee-weon Jung and Soumi Maiti and Shinji Watanabe},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{roshan2023espnet,
+    abbr={Summarization},
+    abbr_publisher={ASRU},
+    title={ESPNet-SUMM: Introducing a novel large dataset, toolkit, and a cross-corpora evaluation of speech summarization systems},
+    author={Roshan Sharma and William Chen and Takatomo Kano and Ruchira Sharma and Atsunori Ogawa and Siddhant Arora and Marc Delcroix and Rita Singh and Shinji Watanabe and Bhiksha Raj},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+
+@inproceedings{fujita2023lvctc,
+    abbr={ASR},
+    abbr_publisher={ASRU},
+    title={LV-CTC: Non-autoregressive ASR with CTC and latent variable models},
+    author={Yuya Fujita and Shinji Watanabe and Xuankai Chang and Takashi Maekaku},
+    booktitle=ASRU,
+    year={2023},
+    publisher={IEEE},
+}
+
+@inproceedings{wang2023unssor,
+    abbr={SS},
+    abbr_publisher={NeurIPS},
+    title={UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures},
+    author={Zhong-Qiu Wang and Shinji Watanabe},
+    booktitle=NeurIPS,
+    year={2023},
+}
+
+@inproceedings{masuyama2023exploring,
+    abbr={SS},
+    abbr_publisher={WASPAA},
+    title={Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation},
+    author={Yoshiki Masuyama and Xuankai Chang and Wangyou Zhang and Samuele Cornell and Zhong-Qiu Wang and Nobutaka Ono and Yanmin Qian and Shinji Watanabe},
+    booktitle=WASPAA,
+    year={2023},
+}
+
 
 @article{maciejewski2023adilemma,
   abbr={SS},

diff --git a/_pages/info.md b/_pages/info.md
@@ -18,6 +18,6 @@ This page has some information guidelines for members of WAVLab.
 
 Our galleries
 
-* [2023 Gallery]({% post_url 2023-04-05-2023-record %})
+* [2023 Gallery]({% post_url 2023-09-24-2023-record %})
 * [2022 Gallery]({% post_url 2022-12-31-2022-record %})
 * [2021 Gallery]({% post_url 2021-12-13-2021-record %})
diff --git a/_pages/sphinx-lunch.md b/_pages/sphinx-lunch.md
@@ -25,10 +25,20 @@ A tentative schedule can be found [here](https://docs.google.com/spreadsheets/d/
 
 ## Future Talks (tentative schedule)
 
+- October 5, 2023
+  - Title: TBD
+  - Speaker: Grant Strimel (Amazon)
 
+- October 12, 2023
+  - Title: Computational Audition through Imprecise labels
+  - Speaker: Ankit Shah
 
 ## Previous Talks
 
+- September 28, 2023
+  - Title: Towards robust speech generation
+  - Speaker: Soumi Maiti
+
 - August 31, 2023
   - Title: Solving problems of a single-modal task with multi-modality
   - Speaker: Minsu Kim (KAIST)

diff --git a/_posts/2023-04-05-2023-record.md b/_posts/2023-04-05-2023-record.md
diff --git a/_posts/2023-09-24-2023-record.md b/_posts/2023-09-24-2023-record.md
@@ -0,0 +1,119 @@
+---
+layout: post
+title: 2023 Activities Gallery
+date: 2023-09-24 11:00:00-0800
+description: This is memory gallery for 2023 activities.
+comments: false
+---
+
+
+<div class="row mt-3">
+<!--     <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.1-2023.jpg" data-zoomable>
+    </div> -->
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.2-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.3-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.4-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.5-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-15.6-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    Three-river cruise at Pittsburgh and Sushi at Kiku, 09.15.2023
+</div>
+
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-07.1-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-07.2-2023.jpg" data-zoomable>
+    </div>
+<!--     <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/09-07.3-2023.jpg" data-zoomable>
+    </div> -->
+</div>
+<div class="caption">
+    Yihan welcome happy hour at Bao, 09.07.2023
+</div>
+
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/07-26.1-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/07-26.2-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    Summer group event at Sourthern Tier Brewery Pittsburgh, 07.25.2023
+</div>
+
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/05-09-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/05-09.2-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    End-of-semester presentation (Spring2023) at CMU and happy hour at Bao, 05.09.2023
+</div>
+
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/04-13-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    Xutai Ma Lab Visit (Guest Lecture) at CMU, 04.13.2023
+</div>
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/04-05-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    Wangyou Welcome Lunch at Bao, 04.05.2023
+</div>
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/3-10.1-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/3-10.2-2023.jpg" data-zoomable>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/3-10.3-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    Post-Interspeech Party at Double Wide Grill, 3.10.2023
+</div>
+
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/gallery/01-27-2023.jpg" data-zoomable>
+    </div>
+</div>
+<div class="caption">
+    End of Takaaki's Internship at LTI, 01.27.2023
+</div>
diff --git a/_posts/2023-12-31-reading-group.md b/_posts/2023-12-31-reading-group.md
@@ -32,3 +32,9 @@ comments: false
 - [Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition](https://arxiv.org/abs/2211.00174)
 - [Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing](https://arxiv.org/abs/2210.13030)
 - [SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training](https://arxiv.org/abs/2210.03730)
+
+### 2023.10.3 ACL 2023 Paper List
+- [SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations](https://aclanthology.org/2023.acl-long.899/)
+- [Efficient Transformers with Dynamic Token Pooling](https://arxiv.org/abs/2211.09761)
+- [A Simple Concatenation can Effectively Improve Speech Translation](https://aclanthology.org/2023.acl-short.153/)
+- [CTC-based Non-autoregressive Speech Translation](https://aclanthology.org/2023.acl-long.744/)