Back to results
US 8,150,691 B2Granted
Arrangement and method for reproducing audio data as well as computer program product for this
AssigneeNuance Communications Austria GmbH
InventorKwaku Frimpong-Ansah
Life of this patent
Estimating the term…
Abstract
During the replaying of audio data stored in a, which audio data corresponds to text data from a text composed of words, the replaying of the audio data in forward and reverse modes is controlled. Starting from particular momentary replay position in the audio data, a backward jump over a return distance corresponding to the length of about at least two words, to a target position, is automatically initiated for the replaying of the audio data in the reverse mode. Then, starting from the particular target position, a replay of the audio data in the forward sequence for just one part of the return distance is undertaken.
Claims25
A system for replaying stored audio data, the system comprising:
- voice recognition means for performing voice recognition on the audio data and generating by the voice recognition means text data and word-marking data, the word-marking data indicating locations of word boundaries between spoken words within the audio data and linking words in the audio data to corresponding words in the text data, wherein the word-marking data is assigned, in the absence of user input, by the voice recognition means to the start of each spoken word in the audio data;
- memory means for storing the audio data and for storing the text data and the word-marking data obtained from performing voice recognition on the audio data;
- audio replaying means for replaying the audio data acoustically in a forward sequence;
- display means for visually displaying the text data;
- and
- control means for controlling the replaying of stored audio data in a forward mode and in a reverse mode, the control means controlling the audio replaying means during a playback of the audio data in the reverse mode to perform a reverse mode playback operation including, starting from a replay position in the audio data initiating a backward jump, counter to the forward sequence, over a distance corresponding to a length of at least N spoken words, to a target position, the control means using the word boundaries indicated in the word-marking data to determine the target position, and then, starting from the target position, the control means initiating a replay of K spoken words of the audio data in the forward sequence using the word boundaries indicated in the word-marking data to determine the end of the replay of the K spoken words, wherein K is less than N, the control means controlling the displaying on the display means of the stored text data that corresponds to the audio data being replayed, as indicated by the word-marking data, the control means further controlling the audio replaying means and the display means to automatically repeat performing the reverse mode playback operation while the system is in the reverse mode, wherein, in the reverse mode, words of the text data are visually highlighted on the display means in sequence, counter to the forward sequence, and, synchronously with each visually highlighted word, a corresponding word in the audio data is replayed acoustically.
3 more elements
A method for replaying audio data stored in at least one memory, the method comprising acts of:
- performing voice recognition, by a voice recognition system, on the audio data and generating text data and word-marking data, the word-marking data indicating locations of word boundaries between spoken words within the audio data and linking words in the audio data to corresponding words in the text data, wherein the word-marking data is assigned, in the absence of user input, by the voice recognition system to the start of each spoken word in the audio data;
- storing the audio data and storing the text data and the word-marking data obtained from performing voice recognition on the audio data;
- controlling the replaying of the audio data in a forward sequence;
- performing a reverse playback operation while in the reverse mode, the reverse playback operation including starting from a replay position in the audio data, automatically performing a backward jump, counter to the forward sequence, over a distance corresponding to a length of at least N spoken words using the word boundaries indicated in the word-marking data, to a target position, including using the word boundaries indicated in the word-marking data to determine the target position, and then, starting from the target position, replaying K spoken words of the stored audio data in the forward sequence using the word boundaries indicated in the word-marking data to determine the end of the replay of the K spoken words;
- displaying the stored text data that corresponds to the audio data being replayed, as indicated by the word-marking data;
- and
- automatically repeating the reverse playback operation while the system is in the reverse mode, wherein, in the reverse mode, words of the text data are visually highlighted on the displayed text data in sequence, counter to the forward sequence, and, synchronously with each visually highlighted word, a corresponding word in the audio data is replayed acoustically.
4 more elements
A system for replaying stored audio data comprising:
- a voice recognition system configured to perform voice recognition on the audio data and to generate text data and word-marking data, the word-marking data indicating locations of word boundaries between spoken words within the audio data and linking words in the audio data to corresponding words in the text data, wherein the word-marking data is assigned, in the absence of user input, by the voice recognition system to the start of each spoken word in the audio data;
- at least one memory configured to store the audio data and to store the text data and the word-marking data obtained from performing voice recognition on the audio data;
- a display device configured to visually display the text data;
- and
- a controller configured to replay the stored audio data in a reverse mode by jumping back N spoken words to a target position using the word boundaries indicated in the word-marking data to determine the target position, playing back K spoken words using the word boundaries indicated in the word-marking data to determine the end of the playback of the K spoken words, and then automatically repeating the jumping and playing back while in the reverse mode, wherein K is less than N, the controller further configured to display on the display device the text data that corresponds to the audio data being replayed, as indicated by the word-marking data, wherein, in the reverse mode, words of the text data are visually highlighted on the display device in sequence, counter to the forward sequence, and, synchronously with each visually highlighted word, a corresponding word in the audio data is replayed acoustically.
2 more elements
Dependencies are inferred from the claim text.