Top Tweets for #INTERSPEECH2021
🎥Happy to share this recording of my oral presentation at #INTERSPEECH2021
✍️CTC-based phonetic aligner with recurrent networks
📄Link to paper: https://t.co/X0Vb0hMOjQ
https://t.co/xVBWf5Bx2I
We will be presenting our proposed #AutoMin2023, and last edition #AutoMin2021 shared task at #INLG2022 in a few minutes @inlgmeeting @ufal_cuni
#minuting #dialogue #summarization #meeting #NLG #NLProc #interspeech2021 #summdial2021 #summdial2022 #INLG2023 #NLP #GenChal
Introducing the @ElitrOrg #minuting corpus at #LREC2022 on automatic #minuting @lrec2022
#NLProc #meeting #summarization
from @ufal_cuni
👉https://t.co/Q1HhWyYlA5
We use the dataset to run our #AutoMin2021 shared task at #Interspeech2021
Overview 👉 https://t.co/JSROSyAgfN
Hello #NLPProc! After a successful 1st edition at #Interspeech2021, we are glad to announce that the 2nd Automatic #Minuting shared task would be at @inlgmeeting 2023
We would present the shared task at #INLG2022
#AutoMin2021 #AutoMin2022 @ElitrOrg #INLG2023
@ufal_cuni
Our pick of the week: Macháček et al. #Interspeech2021 paper "Lost in Interpreting: Speech Translation from Source or Interpreter?". By @sarapapi
https://t.co/C8CaCaGE3Q
#nlproc @INTERSPEECH2021 @MatusZilinec @OndrejBojar
In real-time settings, is it better to translate from the verbose transcription of from the interpreted one? The paper addressed this question via automatic and human evaluations on the new ESIC test corpus. Check these interesting results: https://t.co/MBPDzCfunx
@fbk_mt
Our pick of the week: Zeineldeen et al. #Interspeech2021 paper "Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models". By @mgaido91
https://t.co/9OjZOoQAit
#nlproc @moezeineldeen @albertzeyer @INTERSPEECH2021
A very interesting work on the harm of internal language model learned by E2E ASR models: not all our networks learn is good and try and remove wrong knowledge is definitely an interesting research goal
https://t.co/pjiowUedHf
@fbk_mt
In this publication, Amazon scientists demonstrate that acoustic models trained with an auto-predictive coding loss behave as if they are subject to similar scaling laws. Learn more: https://t.co/Ka4OzldJTK
#AmazonScience #Interspeech2021
See how you can use #NVIDIANemo to fine-tune an English automatic #speechrecognition model on a Japanese dataset from @Mozilla. #Interspeech2021 https://t.co/V1YO9sh4CZ
Check out this #NVIDIANemo Text-to-Speech Notebook, to learn how to control pitch and duration in the FastPitch model during inference. #Interspeech2021 https://t.co/76QZL5dpzk
Our work at #INTERSPEECH2021
At #interspeech2021, we presented an improved method for single channel #speechseparation. This work is the first to show a mix of 20 simultaneous speakers separated from a single channel recording, improving communication across applications. Read more: https://t.co/ErF8v8S3Ut
In this publication, Amazon scientists propose a novel approach that takes advantage of the robustness of warped language models to transcription noise for correcting transcriptions of spoken language. Learn more: https://t.co/ahiCK8bS1B
#AmazonScience #Interspeech2021
Check out this #NVIDIANemo Text-to-Speech Notebook, to learn how to control pitch and duration in the FastPitch model during inference. #Interspeech2021 https://t.co/NWMfol1aza
We proposed a multi-task learning (MTL) framework to simultaneously perform #speechrecognition and emotion classification with an end2end deep neural model. Read more: https://t.co/gEWYTcmRTh #Interspeech2021
At @INTERSPEECH2021, Amazon researchers showed how to use warped language models to correct speech-transcription and ASR errors. In tests, their approach reduced the word error rate of human transcriptions by almost 11%. #AmazonScience #Interspeech2021 https://t.co/dtsJ9sw1GM
Interspeech 2021 - Conference Highlights - Day 3
https://t.co/n38xBLOIJN
@interspeech2021 @seungheeyang2 @ResearchGermany
#INTERSPEECH2021
Congratulations to our PhD Student @AChingacham #projectA4 for receiving the Best Student Paper Award for their work "Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors" #INTERSPEECH2021 🏆
https://t.co/lH3nsiSWkO
＼論文を発表しました／
INTERSPEECH 2021にて以下の論文を発表しました。
Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021
詳しくはこちらをご覧ください。
https://t.co/TeVzeavMem
#音声認識 #INTERSPEECH2021
At #interspeech2021, we presented an improved method for single channel #speechseparation. This work is the first to show a mix of 20 simultaneous speakers separated from a single channel recording, improving communication across applications. Read more: https://t.co/ErF8v8S3Ut
Amazon scientists explore a new research area in privacy-preserving speech recognition that aims to find a middle ground between deleting all data and relying solely on machine transcription versus keeping human transcripts forever: https://t.co/kfBsGBE7ZD #Interspeech2021
See how you can use #NVIDIANemo to fine-tune an English automatic #speechrecognition model on a Japanese dataset from @mozilla. #Interspeech2021 Learn more:
Speech recognition can work better for everyone.
Try out @nvidia NeMo with open #CommonVoice data to create AI models in any language ⤵️
https://t.co/ZcnQj1cvhg
Last Seen Hashtags on Sotwe
Most Popular Users
Elon Musk 
@elonmusk
240.8M followers
Barack Obama
@barackobama
119.2M followers
Donald J. Trump
@realdonaldtrump
111.7M followers
Cristiano Ronaldo
@cristiano
111.3M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.8M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
91.1M followers
KATY PERRY
@katyperry
88.1M followers
Taylor Swift
@taylorswift13
81.9M followers
Lady Gaga
@ladygaga
73.4M followers
Virat Kohli
@imvkohli
70.5M followers
Kim Kardashian
@kimkardashian
70M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
64.1M followers
Neymar Jr
@neymarjr
63.3M followers
The Ellen Show
@theellenshow
62.4M followers
CNN
@cnn
61.9M followers
Selena Gomez
@selenagomez
61.1M followers
X
@x
60.8M followers