Alan W. Black
Carnegie Mellon University
Human–computer interactionLanguage modelSpeech synthesisArtificial intelligenceDomain (software engineering)Dialog boxPattern recognitionNatural languageMachine translationNatural language processingHidden Markov modelUtteranceSentenceQuality (business)Context (language use)Task (project management)Speech recognitionComputer scienceLinguisticsWord (computer architecture)Speech processing
415Publications
66H-index
14.6kCitations
Publications 370
Newest
Aug 30, 2021 in INTERSPEECH (Conference of the International Speech Communication Association)
#1Xinjian Li (CMU: Carnegie Mellon University)H-Index: 6
#2Juncheng Li (CMU: Carnegie Mellon University)H-Index: 11
Last. Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
view all 4 authors...
Source
Aug 30, 2021 in INTERSPEECH (Conference of the International Speech Communication Association)
#1Shruti Palaskar (CMU: Carnegie Mellon University)H-Index: 9
#2Ruslan Salakhutdinov (Carnegie Learning)H-Index: 96
Last. Florian Metze (CMU: Carnegie Mellon University)H-Index: 38
view all 4 authors...
Source
Aug 1, 2021 in ACL (Meeting of the Association for Computational Linguistics)
#1Abhilasha Ravichander (CMU: Carnegie Mellon University)H-Index: 9
#2Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
Last. Norman Sadeh (CMU: Carnegie Mellon University)H-Index: 67
view all 5 authors...
Privacy plays a crucial role in preserving democratic ideals and personal autonomy. The dominant legal approach to privacy in many jurisdictions is the “Notice and Choice” paradigm, where privacy policies are the primary instrument used to convey information to users. However, privacy policies are long and complex documents that are difficult for users to read and comprehend. We discuss how language technologies can play an important role in addressing this information gap, reporting on initial ...
Source
#1Maxine EskenaziH-Index: 37
#2Alan W. BlackH-Index: 66
Last. Yulan FengH-Index: 3
view all 3 authors...
Decomposable tasks are complex and comprise of a hierarchy of sub-tasks. Spoken intent prediction, for example, combines automatic speech recognition and natural language understanding. Existing benchmarks, however, typically hold out examples for only the surface-level sub-task. As a result, models with similar performance on these benchmarks may have unobserved performance differences on the other sub-tasks. To allow insightful comparisons between competitive end-to-end architectures, we propo...
1 Citations
#2Kavya NerellaH-Index: 1
Last. Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
view all 4 authors...
The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library co...
Jun 6, 2021 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Xinjian Li (CMU: Carnegie Mellon University)H-Index: 6
#2Juncheng Li (CMU: Carnegie Mellon University)H-Index: 11
Last. Florian Metze (CMU: Carnegie Mellon University)H-Index: 38
view all 5 authors...
Source
Jun 6, 2021 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Xinjian Li (CMU: Carnegie Mellon University)H-Index: 6
#2David R. Mortensen (CMU: Carnegie Mellon University)H-Index: 10
Last. Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
view all 4 authors...
1 CitationsSource
Jun 6, 2021 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Akshat Gupta (CMU: Carnegie Mellon University)H-Index: 6
#2Xinjian Li (CMU: Carnegie Mellon University)H-Index: 6
Last. Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
view all 4 authors...
With recent advancements in language technologies, humans are now speaking to devices. Increasing the reach of spoken language technologies requires building systems in local languages. A major bottleneck here are the underlying data-intensive parts that make up such systems, including automatic speech recognition (ASR) systems that require large amounts of labelled data. With the aim of aiding development of spoken dialog systems in low resourced languages, we propose a novel acoustics based in...
1 CitationsSource
#1Khyathi Raghavi Chandu (CMU: Carnegie Mellon University)H-Index: 8
#2Yonatan Bisk (CMU: Carnegie Mellon University)H-Index: 23
Last. Alan W. Black (CMU: Carnegie Mellon University)H-Index: 66
view all 3 authors...
The NLP community has seen substantial recent interest in grounding to facilitate interaction between language technologies and the world. However, as a community, we use the term broadly to reference any linking of text to data or non-textual modality. In contrast, Cognitive Science more formally defines "grounding" as the process of establishing what mutual information is required for successful communication between two interlocutors -- a definition which might implicitly capture the NLP usag...