10000 results found.
Kaldi speech recognition engine
Speech Recognizer/Transcriber,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
License:
Apache License v2.0
Size:
None Production Status:
Existing-used
Use:
Speech Recognition/Understanding
-
Paper title:"This is Houston. Say again, please''. The Behavox system for the Apollo-11 Fearless Steps Challenge (phase II).
-
Paper track:13.13 The Fearless Steps Challenge Phase-02/Poster Presentation
-
Paper status:Accept Special Session
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Arseniy Gorin | Kaldi speech recognition engine | /N |
Documentation:
None
DiPCo - Dinner Party Corpus
Speech
Corpus,
Language Type:
Monolingual
Languages:
English
Availability:
Freely Available
License:
CDLA-Permissive
Size:
5 hours Production Status:
Newly created-finished
Use:
Speech Recognition/Understanding
-
Paper title:DiPCo - Dinner Party Corpus
-
Paper track:8.3 Robustness against noise or reverberation/Oral Presentation
-
Paper status:Accept - Poster
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Roland Maas | DiPCo - Dinner Party Corpus | /N |
Documentation:
https://arxiv.org/pdf/1909.13447.pdf
The Switchboard-1 Telephone Speech Corpus
,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
License:
Size:
None Production Status:
Use:
-
Paper title:Neural representations of dialogical history for improving upcoming turn acoustic parameters prediction
-
Paper track:11.4 Conversation, communication and interaction/Oral Presentation
-
Paper status:Accept - Poster
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Simone Fuscone | The Switchboard-1 Telephone Speech Corpus | /N |
Documentation:
None
LibriSpeech
Speech/Written
Corpus,
Language Type:
Monolingual
Languages:
English
Availability:
Freely Available
License:
Size:
982.1 hours Production Status:
Existing-used
Use:
Speech Recognition/Understanding
-
Paper title:Improved hybrid streaming ASR with Transformer language models
-
Paper track:8.5 Novel neural network architectures (e.g. seque/Oral Presentation
-
Paper status:Accept - Oral
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Pau Baquero-Arnal | TED-LIUM | /N |
| Main Contact | Pau Baquero-Arnal | LibriSpeech | /N |
Documentation:
There is publicly available documentation in English
TED-LIUM
Speech/Written
Corpus,
Language Type:
Monolingual
Languages:
English
Availability:
Freely Available
License:
Size:
13 million sentences Production Status:
Existing-used
Use:
Speech Recognition/Understanding
-
Paper title:Improved hybrid streaming ASR with Transformer language models
-
Paper track:8.5 Novel neural network architectures (e.g. seque/Oral Presentation
-
Paper status:Accept - Oral
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Pau Baquero-Arnal | TED-LIUM | /N |
| Main Contact | Pau Baquero-Arnal | LibriSpeech | /N |
Documentation:
There is publicly available documentation in English
Verbmobil
,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
License:
ELRA
Size:
None Production Status:
Use:
-
Paper title:Achieving Multi-Accent ASR via Unsupervised Acoustic Model Adaptation
-
Paper track:8.8 Acoustic model adaptation (e.g. bandwidth, emo/Poster Presentation
-
Paper status:Accept - Poster
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Mehmet Ali Tugtekin Turan | Verbmobil | /N |
Documentation:
None
CAT: A CTC-CRF based ASR Toolkit
Speech
Speech Recognizer/Transcriber,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
Freely Available
License:
Apache-2.0
Size:
400 KByte Production Status:
Newly created-in progress
Use:
Speech Recognition/Understanding
-
Paper title:CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
-
Paper track:8.7 Discriminative acoustic training methods for A/Oral Presentation
-
Paper status:Accept - Oral
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Zhijian Ou | CAT: A CTC-CRF based ASR Toolkit | /N |
Documentation:
None
VoxCeleb 1 and 2
Speech
Corpus,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
Freely Available
License:
OpenSource
Size:
2800 hours Production Status:
Existing-used
Use:
Speaker Verification
-
Paper title:Neural PLDA Modeling for End-to-End Speaker Verification
-
Paper track:4.3 Speaker verification and identification/Poster Presentation
-
Paper status:Accept - Poster
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Shreyas Ramoji | NIST SRE Evaluations | /N |
| Main Contact | Shreyas Ramoji | VoxCeleb 1 and 2 | /N |
Documentation:
None
NIST SRE Evaluations
Speech
Corpus,
Language Type:
Bilingual
Languages:
Tagalog Tunisian Arabic
Availability:
From Data Center(s)
License:
LDC
Size:
3700 hours Production Status:
Existing-used
Use:
Speaker Verification
-
Paper title:Neural PLDA Modeling for End-to-End Speaker Verification
-
Paper track:4.3 Speaker verification and identification/Poster Presentation
-
Paper status:Accept - Poster
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Shreyas Ramoji | NIST SRE Evaluations | /N |
| Main Contact | Shreyas Ramoji | VoxCeleb 1 and 2 | /N |
Documentation:
None
The Munich Versatile and Fast Open-Source Audio Feature Extractor (openSMILE)
Speech
Software Toolkit,
Language Type:
Language Independent
Languages:
<Not Specified>
Availability:
Freely Available
License:
Size:
2 MByte Production Status:
Existing-used
Use:
Feature extraction
-
Paper title:Improving detection of Alzheimer’s Disease using automatic speech recognition to identify high-quality segments for more robust feature extraction
-
Paper track:3.5 Pathological speech and language/Oral Presentation
-
Paper status:Accept - Oral
| Author Number | Name | Affiliation | Country |
|---|---|---|---|
| Main Contact | Yilin Pan | The Munich Versatile and Fast Open-Source Audio Feature Extractor (openSMILE) | /N |
Documentation:
None