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:
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:
Personalized agent services are provided in a personal messaging device, such as a cellular telephone or personal digital assistant, through services of a speech recognizer that converts speech into text and a text-to-speech synthesizer that converts text to speech. Both recognizer and synthesizer may be server-based or locally deployed within the device. The user dictates an e-mail message which is converted to text and stored. The stored text is sent back to the user as text or as synthesized speech, to allow the user to edit the message and correct transcription errors before sending as e-mail. The system includes a summarization module that prepares short summaries of incoming e-mail and voice mail. The user may access these summaries, and retrieve and organize email and voice mail using speech commands.
摘要:
A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.
摘要:
A set of speaker dependent 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. Principle component analysis 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. Environmental adaptation may be performed by including environmental variations in the training data.
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 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:
Electronic commerce (E-commerce) and Voice commerce (V-commerce) proceeds by having the user speak into the system. The user's speech is converted by speech recognizer into a form required by the transaction processor that effects the electronic commerce operation. A dimensionality reduction processor converts the user's input speech into a reduced dimensionality set of values termed eigenvoice parameters. These parameters are compared with a set of previously stored eigenvoice parameters representing a speaker population (the eigenspace representing speaker space) and the comparison is used by the speech model adaptation system to rapidly adapt the speech recognizer to the user's speech characteristics. The user's eigenvoice parameters are also stored for subsequent use by the speaker verification and speaker identification modules.
摘要:
A computer-implemented method and apparatus is provided for processing a spoken request from a user. A speech recognizer converts the spoken request into a digital format. A frame data structure associates semantic components of the digitized spoken request with predetermined slots. The slots are indicative of data which are used to achieve a predetermined goal. A speech understanding module which is connected to the speech recognizer and to the frame data structure determines semantic components of the spoken request. The slots are populated based upon the determined semantic components. A dialog manager which is connected to the speech understanding module may determine at least one slot which is unpopulated based upon the determined semantic components and in a preferred embodiment may provide confirmation of the populated slots. A computer generated-request is formulated in order for the user to provide data related to the unpopulated slot. The method and apparatus are well-suited (but not limited) to use in a hand-held speech translation device.
摘要:
Decision trees are used to store a series of yes-no questions that can be used to convert spelled-word letter sequences into pronunciations. Letter-only trees, having internal nodes populated with questions about letters in the input sequence, generate one or more pronunciations based on probability data stored in the leaf nodes of the tree. The pronunciations may then be improved by processing them using mixed trees which are populated with questions about letters in the sequence and also questions about phonemes associated with those letters. The mixed tree screens out pronunciations that would not occur in natural speech, thereby greatly improving the results of the letter-to-pronunciation transformation.