摘要:
A media production system includes a textual alignment module aligning multiple speech recordings to textual lines of a script based on speech recognition results. A navigation module responds to user navigation selections respective of the textual lines of the script by communicating to the user corresponding, line-specific portions of the multiple speech recordings. An editing module responds to user associations of multiple speech recordings with textual lines by accumulating line-specific portions of the multiple speech recordings in a combination recording based on at least one of relationships of textual lines in the script to the combination recording, and temporal alignments between the multiple speech recordings and the combination recording.
摘要:
Supervised adaptation speech is supplied to the recognizer and the recognizer generates the N-best transcriptions of the adaptation speech. These transcriptions include the one transcription known to be correct, based on a priori knowledge of the adaptation speech, and the remaining transcriptions known to be incorrect. The system applies weights to each transcription: a positive weight to the correct transcription and negative weights to the incorrect transcriptions. These weights have the effect of moving the incorrect transcriptions away from the correct one, rendering the recognition system more discriminative for the new speaker's speaking characteristics. Weights applied to the incorrect solutions are based on the respective likelihood scores generated by the recognizer. The sum of all weights (positive and negative) are a positive number. This ensures that the system will converge.
摘要:
Client speaker locations in a speaker space are used to generate speech models for comparison with test speaker data or test speaker speech models. The speaker space can be constructed using training speakers that are entirely separate from the population of client speakers, or from client speakers, or from a mix of training and client speakers. Reestimation of the speaker space based on client environment information is also provided to improve the likelihood that the client data will fall within the speaker space. During enrollment of the clients into the speaker space, additional client speech can be obtained when predetermined conditions are met. The speaker distribution can also be used in the client enrollment step.
摘要:
A set of speaker dependent models or adapted models is trained upon a comparatively large number of training speakers, one model per speaker, and model parameters are extracted in a predefined order to construct a set of supervectors, one per speaker. Dimensionality reduction is then performed on the set of supervectors to generate a set of eigenvectors that define an eigenvoice space. If desired, the number of vectors may be reduced to achieve data compression. Thereafter, a new speaker provides adaptation data from which a supervector is constructed by constraining this supervector to be in the eigenvoice space based on a maximum likelihood estimation. The resulting coefficients in the eigenspace of this new speaker may then be used to construct a new set of model parameters from which an adapted model is constructed for that speaker. The adapted model may then be further adapted via MAP, MLLR, MLED or the like. The eigenvoice technique may be applied to MLLR transformation matrices or the like; Bayesian estimation performed in eigenspace uses prior knowledge about speaker space density to refine the estimate about the location of a new speaker in eigenspace.
摘要:
The system performs unsupervised speech model adaptation using the recognizer to generate the N-best solutions for an input utterance. Each of these N-best solutions is tested by a reliable information extraction process. Reliable information is extracted by a weighting technique based on likelihood scores generated by the recognizer, or by a non-linear thresholding function. The system may be used in a single pass implementation or iteratively in a multi-pass implementation.
摘要:
The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters. To adapt the parameters with a small amount of enrollment data, an eigenspace is constructed and used to constrain the position of the new speaker so that context independent parameters not provided by the new speaker may be estimated.
摘要:
Speech models are constructed and trained upon the speech of known client speakers (and also impostor speakers, in the case of speaker verification). Parameters from these models are concatenated to define supervectors and a linear transformation upon these supervectors results in a dimensionality reduction yielding a low-dimensional space called eigenspace. The training speakers are then represented as points or distributions in eigenspace. Thereafter, new speech data from the test speaker is placed into eigenspace through a similar linear transformation and the proximity in eigenspace of the test speaker to the training speakers serves to authenticate or identify the test speaker.
摘要:
An improved method is provided for constructing compact acoustic models for use in a speech recognizer. The method includes: partitioning speech data from a plurality of training speakers according to at least one speech related criteria (i.e., vocal tract length); grouping together the partitioned speech data from training speakers having a similar speech characteristic; and training an acoustic bubble model for each group using the speech data within the group.
摘要:
The dynamic programming technique employs a lexical tree that is encoded in computer memory as a flat representation in which the nodes of each generation occupy contiguous memory locations. The traversal algorithm employs a set of traversal rules whereby nodes of a given generation are processed before the parent nodes of that generation. The deepest child generation is processed first and traversal among nodes of each generation proceeds in the same topological direction.
摘要:
An improved method is provided for constructing compact acoustic models for use in a speech recognizer. The method includes: partitioning speech data from a plurality of training speakers according to at least one speech related criteria (i.e., vocal tract length); grouping together the partitioned speech data from training speakers having a similar speech characteristic; and training an acoustic bubble model for each group using the speech data within the group.